History: MRTR conversation grouping + modern message vocabulary (#1705)

* History: MRTR conversation grouping + modern message vocabulary

Teach the Protocol/History view the modern (2026-07-28) message vocabulary,
correlating it off the frames the transport already captures — no change to how
MRTR is driven (manual driving is deferred to #1704).

- Correlation helpers in protocolUtils: extractResultType, extractRequestState,
  extractSubscriptionId, isModernFrame, and groupProtocolEntries — clustering the
  contiguous rounds of one logical operation (original call -> input_required ->
  retried call with a new id -> final result) that share a requestState token.
- New MrtrConversation group renders that cluster as one expandable unit with a
  status derived from the final round, reusing ProtocolEntry for each round.
- ProtocolEntry: resultType badge (input required / complete), a "modern" frame
  badge for server/discover, subscriptions/listen, and the acknowledged
  notification, and a copyable subscriptionId.
- ProtocolListPanel folds each section through the grouping pass and shows an era
  badge in the header. Era is threaded from the negotiated protocolEra
  (App -> InspectorView -> ProtocolScreen -> panel) and never inferred from
  frames, respecting the transcript-classification caveat.
- Shared EraBadge element (+ eraUtils); ConnectionInfoContent reuses it.
- test-servers/configs/modern-mrtr-http.json serves an elicitation tool over the
  modern leg for eyeballing a real MRTR round-trip.
- Pre-bundle @modelcontextprotocol/client in optimizeDeps.include so the
  Storybook vitest project doesn't re-optimize mid-run once protocolUtils pulls
  the client barrel into the browser graph.

Closes #1627

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5

* test-servers: real MRTR tool + live-verified History grouping

While driving the modern flow in the browser, the elicitation-based config
proved unable to produce MRTR: the modern (2026-07-28) SDK server rejects
`server.elicitInput` — server→client requests aren't allowed on that leg; a
tool must instead return `inputRequired(...)`. So the shipped
`modern-mrtr-http.json` (and its README claim) were wrong.

- Add a genuine MRTR tool preset (`mrtr_confirm` / `createMrtrTool`): its handler
  returns `inputRequired({ inputRequests: { confirm: elicit(...) } })` on the
  first call and the final result once the client echoes the answer back on the
  retry.
- Teach the composable test-server to support it: the tool wrapper forwards an
  `InputRequiredResult` verbatim (instead of coercing it to a CallToolResult),
  and `toHandlerExtra` surfaces `inputResponses`/`requestState` so a handler can
  branch between the original call and the retry.
- Point `modern-mrtr-http.json` at the new preset; correct the README to
  describe the real mechanism.
- Add an integration test that drives the full round-trip through InspectorClient
  (auto-fulfilling the embedded elicitation) and asserts the final result is only
  reachable after the input_required round + retry — regression cover that would
  have caught the original config bug.

Verified live in the browser: the History view renders the round-trip as one
grouped "MRTR conversation" (Round 1 input_required → Round 2 complete), keyed by
the real requestState, under the Modern era badge.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5

* Address review notes: dedupe status badge, unique MRTR token, import alias

Non-blocking review feedback on #1705:

- ProtocolEntry: suppress the redundant green "OK" status badge when a
  `resultType` badge already conveys the outcome (a modern success shows only
  `complete`/`input required`). Errors/pending have no `resultType`, so their
  status badge still shows.
- createMrtrTool: mint a unique `requestState` per original call (closure
  counter) so two same-action invocations don't fold into one conversation
  during manual eyeballing. Real SDK tokens are already unique per operation.
- ProtocolEntry: align the `MessageEntry` import to the `@inspector/core` alias
  used by its siblings (was a deep relative path).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5

* Review round 2: green `complete` badge, lighter embedded MRTR container

Non-blocking observations from the second review:

- ProtocolEntry: `resultType` "complete" now renders green (was gray) so a modern
  success keeps the at-a-glance green success affordance a legacy "OK" had, now
  that the redundant OK badge is suppressed. `input_required` stays yellow.
- MrtrConversation: in the narrow monitoring (embedded) column, drop the outer
  container border and tighten padding — the per-round entries are already
  bordered cards, so this avoids a busy border-in-border nesting. The full-width
  view keeps the bordered surface that sets a conversation apart.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5

* Review round 3: module-scope MRTR counter; revert embedded border change

- test-servers: hoist the MRTR `requestState` counter to module scope. The
  modern (2026-07-28) leg is stateless — `createMcpHandler` rebuilds the server
  (and every tool closure) per request — so the previous per-closure counter
  reset to 0 on every request and every token ended in `:1`, defeating its
  purpose. A module-level counter survives the per-request factory recreation
  and increments monotonically across the process, so same-action invocations
  get distinct tokens and don't fold into one conversation. (Review finding.)
- MrtrConversation: revert the embedded borderless/tighter-padding change — per
  maintainer feedback from manual testing, dropping the border didn't improve
  the narrow-column visual, so the group keeps its border in all layouts.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

test-servers/src/composable-test-server.ts

@@ -11,6 +11,7 @@ import {
   ResourceTemplate as SdkResourceTemplate,
   completable,
   isCompletable,
+  isInputRequiredResult,
 } from "@modelcontextprotocol/server";
 import type {
   Implementation,
@@ -19,6 +20,7 @@ import type {
   ResourceTemplateType as ResourceTemplate,
   Prompt,
   CallToolResult,
+  InputRequiredResult,
   PromptArgument,
   RegisteredTool,
   RegisteredResource,
@@ -80,6 +82,16 @@ export interface HandlerExtra {
     method: string;
     params?: Record<string, unknown>;
   }) => Promise<void>;
+  /**
+   * MRTR (2026-07-28): the bare input responses a retried request echoes back,
+   * keyed by the identifiers the server assigned in `inputRequests`. Present
+   * only on the retry round, so an MRTR tool branches on it to distinguish the
+   * original call (return `inputRequired(...)`) from the retry (return the final
+   * result). Undefined on legacy connections and on the first round.
+   */
+  inputResponses?: Record<string, unknown>;
+  /** MRTR: the opaque `requestState` the client echoed on retry (resolved value). */
+  requestState?: unknown;
 }
 
 /** Minimal structural view of `ctx.mcpReq` for building {@link HandlerExtra}. */
@@ -90,6 +102,10 @@ interface McpReqContext {
     signal?: AbortSignal;
     send?: HandlerExtra["sendRequest"];
     notify?: HandlerExtra["sendNotification"];
+    /** MRTR input responses on a retried request (2026-07-28). */
+    inputResponses?: Record<string, unknown>;
+    /** MRTR request-state accessor (resolves the echoed opaque token). */
+    requestState?: () => unknown;
   };
 }
 
@@ -102,6 +118,8 @@ function toHandlerExtra(ctx: ServerContext | undefined): HandlerExtra {
     signal: mcpReq?.signal,
     sendRequest: mcpReq?.send,
     sendNotification: mcpReq?.notify,
+    inputResponses: mcpReq?.inputResponses,
+    requestState: mcpReq?.requestState?.(),
   };
 }
 
@@ -296,7 +314,10 @@ export interface ToolDefinition {
     params: Record<string, unknown>,
     context?: TestServerContext,
     extra?: HandlerExtra,
-  ) => Promise<CallToolResult>;
+    // A handler may return an `InputRequiredResult` (via `inputRequired(...)`)
+    // on the 2026-07-28 leg to drive an MRTR round-trip; the wrapper forwards it
+    // verbatim rather than coercing it to a `CallToolResult`.
+  ) => Promise<CallToolResult | InputRequiredResult>;
 }
 
 export interface TaskToolDefinition {
@@ -745,6 +766,14 @@ export function createMcpServer(config: ServerConfig): McpServer {
               context,
               toHandlerExtra(ctx),
             );
+            // MRTR (2026-07-28): a handler may return an `input_required` result
+            // to request input before completing. Forward it verbatim — the SDK
+            // serves it as the modern input_required result and the client
+            // retries. (Coercing it into a CallToolResult below would strip
+            // `resultType`/`inputRequests`/`requestState`.)
+            if (isInputRequiredResult(result)) {
+              return result;
+            }
             const rawStructured =
               result &&
               typeof result === "object" &&