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>

clients/web/src/components/views/InspectorView/InspectorView.tsx

@@ -38,6 +38,7 @@ import type {
 } from "@inspector/core/mcp/types.js";
 import { isTerminalStatus } from "@inspector/core/mcp/types.js";
 import { isAppTool } from "@inspector/core/mcp/apps.js";
+import { TASKS_EXTENSION_KEY } from "@inspector/core/mcp/modernTaskSchemas.js";
 import { ViewHeader } from "../../groups/ViewHeader/ViewHeader";
 import { VersionBadge } from "../../elements/VersionBadge/VersionBadge";
 import { CopyrightBadge } from "../../elements/CopyrightBadge/CopyrightBadge";
@@ -807,8 +808,11 @@ export function InspectorView({
   //   Logs      → capabilities.logging
   //   Prompts   → capabilities.prompts
   //   Resources → capabilities.resources
-  //   Tasks     → capabilities.tasks (the "run as task" affordance on the
-  //               Tools screen separately keys off tasks.requests.tools.call)
+  //   Tasks     → capabilities.tasks (legacy) OR the
+  //               io.modelcontextprotocol/tasks extension (modern, SEP-2663).
+  //               The "run as task" affordance on the Tools screen separately
+  //               keys off tasks.requests.tools.call (legacy) / the negotiated
+  //               extension (modern).
   //   Apps      → capabilities.tools (MCP Apps build on tools) AND at least one
   //               app tool — Apps is a filtered view of tools, not its own
   //               capability, so it keeps the content check; when app tools
@@ -830,7 +834,12 @@ export function InspectorView({
     const hasApps = hasTools && appTools.length > 0;
     const hasPrompts = capabilities?.prompts !== undefined;
     const hasResources = capabilities?.resources !== undefined;
-    const hasTasks = capabilities?.tasks !== undefined;
+    // Legacy servers gate Tasks on `capabilities.tasks`; modern servers
+    // (SEP-2663) advertise the `io.modelcontextprotocol/tasks` extension in
+    // `server/discover` instead, so gate on either being present.
+    const hasTasks =
+      capabilities?.tasks !== undefined ||
+      capabilities?.extensions?.[TASKS_EXTENSION_KEY] !== undefined;
     const hasLogging = capabilities?.logging !== undefined;
     return ALL_TABS.filter((t) => {
       if (t === NETWORK_TAB && isStdio) return false;
@@ -1314,6 +1323,12 @@ export function InspectorView({
                 ui={toolsUi}
                 listChanged={toolsListChanged}
                 serverSupportsTaskToolCalls={serverSupportsTaskToolCalls}
+                modernTasks={
+                  protocolEra === "modern" &&
+                  initializeResult?.capabilities?.extensions?.[
+                    TASKS_EXTENSION_KEY
+                  ] !== undefined
+                }
                 onUiChange={onToolsUiChange}
                 onRefreshList={onRefreshTools}
                 pagination={toolsPagination}