inspector/core/mcp/samplingCreateMessage.ts
Cliff Hall 9b2c188d11
Some checks failed
Run install, format, lint, build, and test on every push / build (push) Has been cancelled
Run install, format, lint, build, and test on every push / publish (push) Has been cancelled
Run install, format, lint, build, and test on every push / publish-github-container-registry (push) Has been cancelled
MRTR: drive input_required manually to keep pending-request UX (#1704) (#1719)
* MRTR: drive input_required manually to keep pending-request UX (#1704)

Follow-up to #1627/#1705. Instead of letting the SDK auto-fulfil the modern
(2026-07-28) MRTR retry loop, InspectorClient now drives it itself so the
Inspector keeps its pending-request UX, owns the loop, and shows era-accurate
semantics.

Core (core/mcp/inspectorClient.ts):
- Construct the SDK Client with `inputRequired: { autoFulfill: false }`
  (unconditional; a no-op on legacy, which never returns input_required).
- New `requestWithInputRequired()` driver: issues the request with
  `allowInputRequired` + `withInputRequired(schema)`, and while the result is
  `input_required`, fulfils each embedded request through the SAME pending
  sampling/elicitation plumbing, then retries the original call with
  `inputResponses` + the echoed `requestState` on a fresh id, bounded by
  MRTR_MAX_ROUNDS.
- Route tools/call, prompts/get, and resources/read through the driver.
- Embedded roots/list is auto-answered from configured roots (no pending UX);
  decline/cancel is echoed to the server (not treated as an abort); a tool-call
  abort mid-round settles the pending request and surfaces
  ToolCallCancelledError.
- Extract shared `enqueuePendingSample`/`enqueuePendingElicitation` helpers used
  by both the legacy inbound handlers and the driver; add a per-request `origin`
  ("server-request" | "input-required") to the pending wrappers.

Web UI:
- New `MrtrOriginNote` element shows an "input_required — your answer returns as
  a retry" note on a modern MRTR round; legacy panels are unchanged.
- Thread `origin` App -> PendingClientRequestModal -> the sampling/elicitation
  panels (and the inline panels).

Test servers: new MRTR presets (multi-round, roots, sampling, loop, edge-case
param shaping). Integration tests cover the manual round-trip (asserting the
pending UI pauses and the retry carries inputResponses + requestState on a new
id), multi-round, roots auto-answer, sampling, decline-echoed, maxRounds bound,
abort mid-round, and requestState-only/inputRequests-only param shaping.

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

* Review: clarify sampling-reject and between-rounds abort comments (#1704)

Address review nits on PR #1719 (comment-only, no behavior change):
- enqueuePendingSample docstring: sampling has no decline/cancel action; the
  panel either sends a result (resolve) or Rejects (reject → fails the call).
  The shared "declined/cancelled resolves" wording was accurate only for the
  elicitation case.
- callToolWithRetries abort comment: note the between-rounds case — when the
  abort lands while an MRTR round awaits an embedded pending request there is no
  in-flight SDK request, so nothing is sent on the wire; the outcome
  (ToolCallCancelledError, no failed-call record) is identical.

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

* test-servers: add mrtr-showcase config exercising every MRTR preset (#1704)

A single modern-era streamable-HTTP server (port 3111) bundling all six MRTR
presets — mrtr_confirm, mrtr_two_step, mrtr_sample, mrtr_roots, mrtr_edge,
mrtr_loop — for manual testing of the manual-driving pending-request UX across
single-round, multi-round, sampling, roots, param-shaping, and maxRounds paths.
Document it in the README alongside modern-mrtr-http.json.

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>
2026-07-17 23:15:19 -04:00

95 lines
2.9 KiB
TypeScript

import type {
CreateMessageRequest,
CreateMessageResult,
} from "@modelcontextprotocol/client";
import { RELATED_TASK_META_KEY } from "@modelcontextprotocol/client";
import type { PendingRequestOrigin } from "./types.js";
export type { CreateMessageRequest, CreateMessageResult };
/**
* Data shape of a pending sampling request tracked by the InspectorClient.
* v2's state/screen layer consumes this interface; the runtime class below
* (SamplingCreateMessage) implements it.
*/
export interface InspectorPendingSampling {
id: string;
timestamp: Date;
request: CreateMessageRequest;
taskId?: string;
origin: PendingRequestOrigin;
}
/**
* Represents a pending sampling request from the server
*/
export class SamplingCreateMessage {
public readonly id: string;
public readonly timestamp: Date;
public readonly request: CreateMessageRequest;
public readonly taskId?: string;
/**
* How this request reached the Inspector — a legacy server→client request or
* a modern MRTR `input_required` round. Drives era-accurate copy in the
* pending-request UI. Defaults to `"server-request"` so existing call sites
* (and stories) keep the legacy semantics unchanged.
*/
public readonly origin: PendingRequestOrigin;
private resolvePromise?: (result: CreateMessageResult) => void;
private rejectPromise?: (error: Error) => void;
private onRemove: (id: string) => void;
constructor(
request: CreateMessageRequest,
resolve: (result: CreateMessageResult) => void,
reject: (error: Error) => void,
onRemove: (id: string) => void,
origin: PendingRequestOrigin = "server-request",
) {
this.onRemove = onRemove;
this.id = `sampling-${crypto.randomUUID()}`;
this.timestamp = new Date();
this.request = request;
// Extract taskId from request params metadata if present
const relatedTask = request.params?._meta?.[RELATED_TASK_META_KEY];
this.taskId = relatedTask?.taskId;
this.origin = origin;
this.resolvePromise = resolve;
this.rejectPromise = reject;
}
/**
* Respond to the sampling request with a result
*/
async respond(result: CreateMessageResult): Promise<void> {
if (!this.resolvePromise) {
throw new Error("Request already resolved or rejected");
}
this.resolvePromise(result);
this.resolvePromise = undefined;
this.rejectPromise = undefined;
// Remove from pending list after responding
this.remove();
}
/**
* Reject the sampling request with an error
*/
async reject(error: Error): Promise<void> {
if (!this.rejectPromise) {
throw new Error("Request already resolved or rejected");
}
this.rejectPromise(error);
this.resolvePromise = undefined;
this.rejectPromise = undefined;
// Remove from pending list after rejecting
this.remove();
}
/**
* Remove this pending sample from the list
*/
remove(): void {
this.onRemove(this.id);
}
}