FE-1506: Show captures and completion while a panel elicitation runs

apps/brunch-agent/test/baseline-harness.test.ts

@@ -14,6 +14,9 @@ import { runNodeScript } from "./run-node-script";
 
 import type { HarnessRunRecord } from "../../../libs/@hashintel/brunch-agent/evaluations/protocols/process-model-elicitation/baseline/harness-run.ts";
 
+const isRecord = (value: unknown): value is Record<string, unknown> =>
+  typeof value === "object" && value !== null;
+
 const testDirectory = import.meta.dirname;
 const contextRoot = join(
   testDirectory,
@@ -94,6 +97,48 @@ test("condition 5 drives the shipped elicitor through the binding and reads the
     captures: 1,
     complete: false,
   });
+  const appliedSweepPart = run.history.messages
+    .flatMap((message) => message.parts)
+    .find(
+      (part) =>
+        part.type === "dynamic-tool" &&
+        part.toolName === "brunch_sweep" &&
+        part.state === "output-available",
+    );
+  if (
+    appliedSweepPart?.type !== "dynamic-tool" ||
+    appliedSweepPart.state !== "output-available" ||
+    !isRecord(appliedSweepPart.output)
+  ) {
+    throw new Error("The applied sweep did not expose its result.");
+  }
+  expect(appliedSweepPart.output.status).toBe("applied");
+  const sweepCaptures = appliedSweepPart.output.captures;
+  if (!Array.isArray(sweepCaptures) || !isRecord(sweepCaptures[0])) {
+    throw new Error("The sweep did not expose its current captures.");
+  }
+  expect(sweepCaptures).toHaveLength(1);
+  expect(sweepCaptures[0].status).toBe("active");
+  const { evidence } = sweepCaptures[0];
+  expect(Array.isArray(evidence)).toBe(true);
+  if (!Array.isArray(evidence) || !isRecord(evidence[0])) {
+    throw new Error("The capture did not expose its evidence.");
+  }
+  expect(evidence[0].excerpt).toBe(EXPERT_OBJECTIVE_QUOTE);
+  const { completion } = appliedSweepPart.output;
+  if (!isRecord(completion) || !Array.isArray(completion.failures)) {
+    throw new Error("The sweep did not expose its completion report.");
+  }
+  expect(completion.complete).toBe(false);
+  expect(completion.failures).toHaveLength(5);
+  expect(
+    completion.failures.every(
+      (failure) =>
+        isRecord(failure) &&
+        typeof failure.diagnostic === "string" &&
+        typeof failure.message === "string",
+    ),
+  ).toBe(true);
 
   // Then the interviewer closes without asking; the runner counts three such
   // turns before the wrap and declares the interview stalled — no classifier.

apps/petrinaut-website/src/main/app/local-storage-demo/brunch-panel-transport.test.ts

@@ -0,0 +1,247 @@
+import { expect, test } from "vitest";
+
+import { createBrunchPanelTransport } from "./brunch-panel-transport";
+
+import type { PetrinautAiChatTransport } from "@hashintel/petrinaut/ui";
+import type { UIMessageChunk } from "ai";
+
+const sweepChunks: UIMessageChunk[] = [
+  {
+    type: "tool-input-available",
+    toolCallId: "no-range",
+    toolName: "brunch_sweep",
+    input: {},
+  },
+  {
+    type: "tool-output-available",
+    toolCallId: "no-range",
+    output: { status: "no-settled-range" },
+  },
+  {
+    type: "tool-input-available",
+    toolCallId: "refused",
+    toolName: "brunch_sweep",
+    input: {},
+  },
+  {
+    type: "tool-output-available",
+    toolCallId: "refused",
+    output: {
+      status: "refused",
+      refusal: {
+        code: "evidence-quote-not-found",
+        message: "Use an exact quote.",
+      },
+    },
+  },
+  {
+    type: "tool-input-available",
+    toolCallId: "applied",
+    toolName: "brunch_sweep",
+    input: {},
+  },
+  {
+    type: "tool-output-available",
+    toolCallId: "applied",
+    output: {
+      status: "applied",
+      appliedCaptureIds: ["capture-1"],
+      captures: [
+        {
+          id: "capture-1",
+          status: "active",
+          epistemicStatus: "explicit",
+          confidence: "high",
+          content: { value: { type: "slot-asserted" } },
+          evidence: [{ excerpt: "Line A runs next." }],
+        },
+        {
+          id: "capture-old",
+          status: "superseded",
+          epistemicStatus: "inferred",
+          confidence: "medium",
+          content: { absence: "unknown" },
+          basis: {
+            type: "default-rule",
+            description: "The earlier default.",
+          },
+          alternativeGroup: "line-a-owner",
+        },
+        {
+          id: "capture-withdrawn",
+          status: "retracted",
+          epistemicStatus: "explicit",
+          confidence: "high",
+          content: { value: "Sam" },
+          evidence: [{ excerpt: "Not Sam after all." }],
+          supersedes: "capture-old",
+        },
+      ],
+      completion: {
+        complete: false,
+        pluginVersion: "1.0.0",
+        revision: "revision-1",
+        failures: [
+          {
+            diagnostic: "unaddressed",
+            nodeId: "activity:line-a",
+            kind: "activity",
+            slot: "owner",
+            requirement: "named",
+            actual: "not mentioned",
+            message: "The owner is missing.",
+            captureIds: ["capture-1"],
+          },
+        ],
+        sliceNodeIds: ["activity:line-a"],
+        outsideSlice: [
+          {
+            nodeId: "activity:Line-B",
+            kind: "activity",
+            open: [
+              {
+                diagnostic: "unaddressed",
+                nodeId: "activity:Line-B",
+                kind: "activity",
+                slot: "Owner",
+                requirement: "named",
+                actual: "not mentioned",
+                message: "The owner is missing.",
+                captureIds: ["Capture-2"],
+              },
+            ],
+          },
+        ],
+      },
+    },
+  },
+];
+
+const sourceTransport: PetrinautAiChatTransport = {
+  reconnectToStream: async () => null,
+  sendMessages: async () =>
+    new ReadableStream({
+      start(controller) {
+        for (const chunk of sweepChunks) controller.enqueue(chunk);
+        controller.close();
+      },
+    }),
+};
+
+const readChunks = async (
+  stream: ReadableStream<UIMessageChunk>,
+): Promise<UIMessageChunk[]> => {
+  const chunks: UIMessageChunk[] = [];
+  for await (const chunk of stream) chunks.push(chunk);
+  return chunks;
+};
+
+test("makes every Brunch sweep outcome readable in the panel", async () => {
+  const transport = createBrunchPanelTransport(sourceTransport);
+  const stream = await transport.sendMessages({} as never);
+  const chunks = await readChunks(stream);
+  const outputs = chunks.filter(
+    (chunk) => chunk.type === "tool-output-available",
+  );
+
+  expect(outputs.map((outputChunk) => outputChunk.output)).toEqual([
+    {
+      status: "no-settled-range",
+      title: "No settled range to sweep",
+      detail: "The conversation has no settled user entries.",
+    },
+    {
+      status: "refused",
+      refusal: {
+        code: "evidence-quote-not-found",
+        message: "Use an exact quote.",
+      },
+      title: "Sweep refused",
+      detail: "Use an exact quote.",
+      items: ["Refusal: evidence-quote-not-found"],
+    },
+    {
+      status: "applied",
+      appliedCaptureIds: ["capture-1"],
+      captures: [
+        {
+          id: "capture-1",
+          status: "active",
+          epistemicStatus: "explicit",
+          confidence: "high",
+          content: { value: { type: "slot-asserted" } },
+          evidence: [{ excerpt: "Line A runs next." }],
+        },
+        {
+          id: "capture-old",
+          status: "superseded",
+          epistemicStatus: "inferred",
+          confidence: "medium",
+          content: { absence: "unknown" },
+          basis: {
+            type: "default-rule",
+            description: "The earlier default.",
+          },
+          alternativeGroup: "line-a-owner",
+        },
+        {
+          id: "capture-withdrawn",
+          status: "retracted",
+          epistemicStatus: "explicit",
+          confidence: "high",
+          content: { value: "Sam" },
+          evidence: [{ excerpt: "Not Sam after all." }],
+          supersedes: "capture-old",
+        },
+      ],
+      completion: {
+        complete: false,
+        pluginVersion: "1.0.0",
+        revision: "revision-1",
+        failures: [
+          {
+            diagnostic: "unaddressed",
+            nodeId: "activity:line-a",
+            kind: "activity",
+            slot: "owner",
+            requirement: "named",
+            actual: "not mentioned",
+            message: "The owner is missing.",
+            captureIds: ["capture-1"],
+          },
+        ],
+        sliceNodeIds: ["activity:line-a"],
+        outsideSlice: [
+          {
+            nodeId: "activity:Line-B",
+            kind: "activity",
+            open: [
+              {
+                diagnostic: "unaddressed",
+                nodeId: "activity:Line-B",
+                kind: "activity",
+                slot: "Owner",
+                requirement: "named",
+                actual: "not mentioned",
+                message: "The owner is missing.",
+                captureIds: ["Capture-2"],
+              },
+            ],
+          },
+        ],
+      },
+      title: "Sweep applied",
+      detail: "1 new capture · 3 total · incomplete",
+      items: [
+        'Capture capture-1 (active; explicit; confidence high): {"type":"slot-asserted"} — “Line A runs next.”',
+        "Capture capture-old (superseded; inferred; confidence medium): absence: unknown — default-rule: The earlier default.; alternative group line-a-owner",
+        'Capture capture-withdrawn (retracted; explicit; confidence high): "Sam" — “Not Sam after all.”; supersedes capture-old',
+        "Completion: incomplete · plugin 1.0.0 · revision revision-1",
+        "Completion slice: activity:line-a",
+        "Completion gap [unaddressed] at activity:line-a.owner: needs named; actual not mentioned. The owner is missing. Captures: capture-1",
+        "Outside completion slice: activity:Line-B (activity); 1 open requirement",
+        "Outside-slice Completion gap [unaddressed] at activity:Line-B.Owner: needs named; actual not mentioned. The owner is missing. Captures: Capture-2",
+      ],
+    },
+  ]);
+});