Tasks: io.modelcontextprotocol/tasks extension on modern servers (era fork) (#1731)

* Tasks: modern io.modelcontextprotocol/tasks extension (era fork core)

Core + test-server implementation of the SEP-2663 tasks extension for modern
(2026-07-28) connections, forked from the legacy 2025-11-25 tasks path.

SDK v2 removed all tasks support AND era-gates the tasks/* spec methods out of
the modern era on both the client (outbound) and server (inbound) sides, and its
codec rejects a resultType:"task" result outright. So the Inspector drives the
extension itself: task creation rides tools/call (a modern method) with the
resultType:"task" frame rewritten at the transport to a CallToolResult carrying
the handle in _meta; tasks/get/update/cancel go over a raw-wire request channel
that bypasses the era gate (full modern envelope, string ids, consumed by the
transport). input_required tasks reuse the existing pending-request modal via
fulfilInputRequests, answered with tasks/update. No tasks/list, no tasks/result.

Tab + run-as-task gate on the negotiated extension; the managed task store's
refresh re-polls known handles on modern (no server list). Test server serves
the extension via an Express interceptor (SDK can't) + a shared poll-driven
runtime. Full integration coverage of both eras.

Refs #1631

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

* Tasks modern era: tests + coverage (raw-wire, schemas, era integration)

Adds unit coverage for modernTaskSchemas and the raw-wire request channel
(transport-null guard, send failure, timeout, error response, teardown), plus
end-to-end era integration tests (create/poll/input-required/update/cancel,
synchronous passthrough, unknown-id error, modern store re-poll). Fixes the App
and constructor-capabilities tests for the always-on tasks extension.

Refs #1631

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

* Tasks modern era: docs + share test servers per era to de-flake coverage

Document the tasks era-fork test configs in README and the new core/test-server
files in AGENTS.md. Share one modern + one legacy test server across the era
integration block (started lazily, stopped in afterAll) — starting a fresh
Express server per test made connection negotiation flaky under the heavy
concurrent coverage run.

Refs #1631

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

* Restore pr-screenshots deleted inadvertently

The logging/subscriptions PR screenshots + README were staged-deleted in the
working tree before this branch; restore them from v2/main so this PR doesn't
remove other PRs' artifacts.

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

* Tasks modern era: offer Run-as-task for any tool + PR screenshots

On modern (SEP-2663) task creation is server-directed — the client declares the
extension once and any tool may return a task — so the Tools screen now offers
'Run as task' for every tool on a modern connection (threaded via a modernTasks
prop through InspectorView → ToolsScreen → ToolDetailPanel), rather than gating
on the legacy per-tool taskSupport. Verified end-to-end in the web UI (remote
proxy): create → poll tasks/get → input_required elicitation → tasks/update →
inline result, plus the unchanged legacy tasks/list/result flow. Adds proof
screenshots.

Refs #1631

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

* Tasks modern era: address two follow-ups (task-input note + ordinary-path auto-poll)

1. The pending-request note now distinguishes a modern task round from an MRTR
   round: a new 'task-input-required' PendingRequestOrigin threads through
   fulfilInputRequests → the pending-request modal → MrtrOriginNote, which shows
   'submitted via a tasks/update request (SEP-2663), not a retry' instead of the
   MRTR retry copy.

2. The ordinary (non-run-as-task) modern callTool path now auto-polls an
   unsolicited task handle: attemptToolCall detects the rewritten handle in the
   result _meta and drives it to termination (get → input_required/update →
   inline result), dispatching task events so the Tasks tab + toasts track it and
   the tool result resolves to the task's final result. The poll loop is shared
   with the streaming path via extracted helpers (submitModernTaskInput /
   modernTaskTerminalOutcome / modernTaskPollInterval).

Refs #1631

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

* Tasks modern era: address review (negotiated envelope version, input-round cap, clarifying comment) + fresh smoke screenshots

Review of #1731:
1. withModernTaskEnvelope now stamps the NEGOTIATED protocol version
   (getProtocolVersion() ?? MODERN_PROTOCOL_VERSION) so the envelope matches the
   MCP-Protocol-Version header instead of a hardcoded constant.
2. A never-completing input_required task is now bounded by MRTR_MAX_ROUNDS in the
   shared submitModernTaskInput (threaded through both poll loops), so a
   non-conformant server can't re-prompt the user forever. New modern_loop_task
   test-server tool + integration test cover the cap.
3. ToolDetailPanel: comment clarifying that per-tool taskSupport:"forbidden" is
   deliberately ignored on modern (task creation is server-directed under SEP-2663).

(The abort-during-poll observation is addressed in the PR reply: the cancel path
uses tasks/cancel and disconnect rejects the in-flight raw request, so the poll
stops; matches legacy.)

Fresh web-UI smoke screenshots (modern connected, task completed, input_required
with the corrected tasks/update note, input completed).

Refs #1631

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

* Tasks modern era: fix uncancelable input-required loop + sticky cancel

Two bug fixes reported during manual testing of the tasks era-fork (#1631):

1. A modern task paused at `input_required` (e.g. `modern_loop_task`, which
   never advances) could not be cancelled: the poll loop blocked on the
   pending-request modal, so `cancelRequestorTask` sent `tasks/cancel` but the
   modal kept re-prompting. Now each modern poll loop registers a per-task
   AbortController (`registerTaskInputAbort`), `cancelRequestorTask` aborts it
   to reject the pending elicitation and unblock the poll, and the embedded
   input requests are tagged with their owning task id
   (`RELATED_TASK_META_KEY`) so the pending-request UI's Cancel action cancels
   the TASK rather than sending a "cancel" answer the server would re-prompt on.

2. On the legacy server, cancelling a task briefly showed CANCELLED then
   flipped to COMPLETED when the in-flight tool call resolved. Cancellation is
   a deliberate terminal decision, so `ManagedRequestorTasksState` now remembers
   cancelled task ids and ignores any later non-cancelled status update.

Also: move the compact task id onto its own line in the embedded monitoring
sidebar so the status badge / Cancel Task control don't wrap; DRY the duplicated
task poll-interval logic into a shared `taskPollInterval` helper.

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

* Refresh tasks PR screenshots + capture both bug-fix scenarios

Recapture the five tasks flow screenshots against the current build and add
two demonstrating the post-review fixes: modern_loop_task cancelled from the
pending-request modal (uncancelable-loop fix) and a legacy task staying
CANCELLED after the in-flight call resolves (sticky-cancel fix).

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

* Address re-review: sticky cancel on legacy refresh + App cancel-routing test

Re-review of the cancelable-loop / sticky-cancel fix raised two non-blocking
hardening items:

1. The legacy tasks/list refresh() rebuilt the list from the server, honoring
   only dismissedTaskIds — so a cooperative-cancel server that re-lists a
   user-cancelled task as completed could un-stick the cancel on a manual
   Refresh. The refresh path now pins a cancelledTaskIds task to "cancelled"
   (keeping it visible-as-cancelled, matching the live-merge handlers) rather
   than dropping it. Covered by a new state test.

2. Added an App.test.tsx case locking in the user-facing half of the fix: Cancel
   on a task-input-required elicitation calls cancelRequestorTask (not respond).

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

@@ -43,6 +43,12 @@ import {
   ListTasksRequestSchema,
   TaskStatusNotificationSchema,
 } from "@modelcontextprotocol/core";
+import {
+  TASKS_EXTENSION_KEY,
+  ModernTaskRuntime,
+  createModernTaskTools,
+  wireModernTaskHandlers,
+} from "./modern-tasks.js";
 
 // Empty object JSON schema constant (from SDK's mcp.js)
 const EMPTY_OBJECT_JSON_SCHEMA = {
@@ -479,6 +485,21 @@ export interface ServerConfig {
    * Only used if tasks capability is enabled.
    */
   taskStore?: InMemoryTaskStore;
+  /**
+   * Advertise the modern (2026-07-28) `io.modelcontextprotocol/tasks` extension
+   * (SEP-2663) and wire its raw `tasks/get` / `tasks/update` / `tasks/cancel`
+   * handlers plus the `modern_task` / `modern_input_task` tools. Distinct from
+   * the legacy {@link ServerConfig.tasks} capability — meant to be paired with
+   * `modern: true`. See `modern-tasks.ts`.
+   */
+  tasksExtension?: boolean;
+  /**
+   * Shared modern task runtime. Created lazily on first `createMcpServer` call
+   * and cached here so the stateless modern leg's per-request server instances
+   * share one task store (a task created by a `tools/call` must be visible to a
+   * later `tasks/get`). Do not set by hand.
+   */
+  modernTaskRuntime?: ModernTaskRuntime;
   /**
    * OAuth 2.1 configuration for test server.
    * - **combined** (default): this server is both MCP resource and authorization server.
@@ -615,9 +636,13 @@ export function createMcpServer(config: ServerConfig): McpServer {
       cancel?: object;
       requests?: { tools?: { call?: object } };
     };
+    extensions?: Record<string, object>;
   } = {};
 
-  if (config.tools !== undefined) {
+  // The modern tasks extension (SEP-2663) needs the tools capability too (its
+  // task-augmented tools list via `tools/list`), even when no `config.tools`
+  // were supplied.
+  if (config.tools !== undefined || config.tasksExtension) {
     capabilities.tools = {};
   }
   if (
@@ -651,6 +676,19 @@ export function createMcpServer(config: ServerConfig): McpServer {
     }
   }
 
+  // Modern tasks extension (SEP-2663): advertise it in server/discover and reuse
+  // (or lazily create + cache) the shared runtime so the stateless modern leg's
+  // per-request servers all answer against the same task store.
+  const modernTaskRuntime = config.tasksExtension
+    ? (config.modernTaskRuntime ??= new ModernTaskRuntime())
+    : undefined;
+  if (config.tasksExtension) {
+    capabilities.extensions = {
+      ...(capabilities.extensions ?? {}),
+      [TASKS_EXTENSION_KEY]: {},
+    };
+  }
+
   // Create the in-memory task store if tasks are enabled. SDK v2 has no built-in
   // task runtime, so the store is owned here and its methods answer the wire.
   const taskStore =
@@ -746,9 +784,15 @@ export function createMcpServer(config: ServerConfig): McpServer {
   // (returning a task handle), reproducing the deleted SDK task runtime.
   const taskTools = new Map<string, TaskToolDefinition>();
 
-  // Set up tools
-  if (config.tools && config.tools.length > 0) {
-    for (const tool of config.tools) {
+  // Set up tools. The modern tasks extension contributes its task-augmented
+  // tools (registered as ordinary tools so they surface in `tools/list`; their
+  // `tools/call` is intercepted by `wireModernTaskHandlers` below).
+  const effectiveTools: (ToolDefinition | TaskToolDefinition)[] = [
+    ...(config.tools ?? []),
+    ...(config.tasksExtension ? createModernTaskTools() : []),
+  ];
+  if (effectiveTools.length > 0) {
+    for (const tool of effectiveTools) {
       if (isTaskTool(tool)) {
         // Register the task tool as an ordinary tool so it surfaces in
         // `tools/list` with its input schema, `_meta`, and `execution` support.
@@ -1254,6 +1298,12 @@ export function createMcpServer(config: ServerConfig): McpServer {
     wireTaskHandlers(mcpServer, taskStore, taskTools);
   }
 
+  // Modern tasks extension (SEP-2663): raw tasks/get, tasks/update, tasks/cancel
+  // (no tasks/list, no tasks/result) plus the CreateTaskResult tools/call seam.
+  if (modernTaskRuntime) {
+    wireModernTaskHandlers(mcpServer, modernTaskRuntime);
+  }
+
   return mcpServer;
 }