experiment(re): distinguish point facts from object selectors

Apply the interior-reference counterexample to the facade: label exact-address scope and emit location endpoints while preserving caller selectors separately. Carry canonical target-content provenance through experimental MCP replies and verify it on the real client. Keep original measurements pinned to the v1 response shape. Nine experiment checks and real Kuna lifecycle/context checks pass.

Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>

experiments/atomic-re-tools/README.md

@@ -120,6 +120,13 @@ shape remain the same; ordinary queries do not materialize the richer facts.
 Experimental MCP tools have live-validated input schemas, but no canonical
 output-schema/product-catalog integration. They are not a production SDK/API.
 
+The v2 facade labels reference scope explicitly and connects **locations** in its
+point-reference edges. A result's `target` preserves the caller's selector; it
+is not a separate observation proving that an object exists at that address.
+All experimental MCP results carry REA's canonical untrusted-target-content
+marker. The v1 measurement table is retained with its revision label; it is not
+relabelled as a measurement of this later response shape.
+
 ## Reproduce
 
 Use the repository's pinned Node/npm and run `npm ci`, then

experiments/atomic-re-tools/benchmark.mjs

@@ -58,6 +58,12 @@ const call = async (name, arguments_ = {}, expectError = false) => {
     { timeout: 180000 },
   );
   wire.push({ request: { name, arguments: arguments_ }, response, phase });
+  if (name.startsWith("experiment_"))
+    assert.equal(
+      response._meta?.provenance?.untrusted_content,
+      true,
+      "Experimental results lost the canonical target-content marker",
+    );
   calls.push({ name, phase, elapsed_ms: performance.now() - started });
   if (expectError) {
     assert.equal(response.isError, true);

experiments/atomic-re-tools/facts.mjs

@@ -104,6 +104,7 @@ export class FactQueries {
       results.push({
         target,
         status: "ok",
+        scope: { kind: "exact-address", address: target.address },
         ...source(evidence),
         selection: page.selection,
         coverage: {
@@ -113,7 +114,7 @@ export class FactQueries {
         },
         items: page.items.map((address) => ({
           from: { kind: "location", address },
-          to: target,
+          to: { kind: "location", address: target.address },
           kind: "unknown",
           kind_reason: "The existing xrefs contract projects addresses only.",
         })),

experiments/atomic-re-tools/facts.test.mjs

@@ -77,7 +77,7 @@ test("partial batches retain good observations and exact failure reasons", async
   assert.equal(result.results[0].coverage.status, "unknown");
 });
 
-test("duplicate selectors share work but preserve separate string identities", async () => {
+test("duplicate point lookups share work without turning selectors into observed objects", async () => {
   let calls = 0;
   const facts = new FactQueries(
     port(async () => {
@@ -92,9 +92,14 @@ test("duplicate selectors share work but preserve separate string identities", a
   });
   assert.equal(calls, 1);
   assert.deepEqual(
-    result.results.map((row) => row.items[0].to),
+    result.results.map((row) => row.target),
     [string, otherEncoding, string],
   );
+  assert.deepEqual(
+    result.results.map((row) => row.items[0].to),
+    Array(3).fill({ kind: "location", address: string.address }),
+  );
+  assert.equal(result.results[0].scope.kind, "exact-address");
 });
 
 test("paging and field selection retain identities, source and unknown coverage", async () => {

experiments/atomic-re-tools/results.md

@@ -154,10 +154,8 @@ The exact-address composition therefore returns **unknown**, not a guessed
 nearby line. The mapped-code run cost 8.387 s / 8.091 CPU s / 202.0 MiB, including
 discovery/references and decompilation. It did not finish the analyst question
 "which condition triggers the error?" and must not count as a successful
-context-saving answer. A development attempt also used an unsupported
-single-function timeout flag; it failed and was corrected after checking actual
-CLI help. Single-function work uses REA's owned command deadline and native
-`--max-fn-memory`; it does not accept the batch `--max-fn-seconds` flag.
+context-saving answer. Single-function work uses REA's owned command deadline
+and the native `--max-fn-memory` option shown by the tested CLI's actual help.
 
 The retained C text does contain the error literal at line 164, but a small
 fixed window there omits the earlier check around lines 122–124. Literal search
@@ -190,6 +188,11 @@ does not claim to have completed that trial.
   paging, duplicate-selector, negative/unknown, retained-Evidence, foreign-context
   and expired-lease checks. Its live catalog had 212 tools and zero output
   schemas. Verification runs are excluded from the performance table.
+- The v2 facade was also exercised through a real Kuna MCP client: edges carry
+  explicit point scope and location endpoints, caller selectors stay separate,
+  and successful/error results retain the canonical untrusted-target marker.
+  The same six additional verification groups passed. This v2 verification is
+  not relabelled as a new performance comparison.
 - All real-provider measurements reported verified cleanup and zero OOM kills.
   No default parallel-suite stability, live-model reasoning improvement, general
   high-address code mapping, overlay support or newer Kuna compatibility is claimed.

experiments/atomic-re-tools/server.mjs

@@ -6,6 +6,7 @@ import { createServer } from "../../dist/server/createServer.js";
 import { createEvidence } from "../../dist/domain/evidence.js";
 import { projectAnalysisError } from "../../dist/domain/analysisErrorProjection.js";
 import { toolContract } from "../../dist/contracts/toolContracts.js";
+import { TARGET_CONTENT_RESULT_META } from "../../dist/server/toolResultEncoding.js";
 import { expandProviderCapabilities } from "../../dist/contracts/toolOutputSchemaPrimitives.js";
 import { FactQueries, contextFor } from "./facts.mjs";
 
@@ -63,6 +64,7 @@ const contracts = [
 ];
 
 const encode = (value) => ({
+  _meta: TARGET_CONTENT_RESULT_META,
   content: [{ type: "text", text: JSON.stringify(value) }],
   structuredContent: value,
   ...(value.status === "error" ? { isError: true } : {}),