@openwop/openwop-conformance 2.42.0 → 2.42.1

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # `@openwop/openwop-conformance` Changelog
 
+## [2.42.1] — 2026-09-26 — RFC 0111's live witness scenarios outlast a real host, and the MCP run-transport leg identifies its own run
+
+- **RFC 0111's live scenarios no longer die at vitest's 30 s default.** `context-budget-transcript-bound` and `context-summarization-replay` drive the live-model fixture `conformance-context-budget-live` (six real model turns and six child runs; 30–40 s per run on MyndHyve production, 2026-09-26), and the global `testTimeout: 30_000` killed both before any assertion — which `OPENWOP_POLL_TIMEOUT_SCALE` could not reach. Each now carries a per-test timeout from `liveScenarioTimeoutMs(runs)` (`src/lib/polling.ts`: the scaled sum of `LIVE_RUN_POLL_MS` = 180 s per run plus 60 s for seam reads — 240 s / 420 s at scale 1) and polls with `{ timeoutMs: LIVE_RUN_POLL_MS }`, so the named poll deadline always fires before the test deadline, at every scale. The global timeout is unchanged. Self-test: `src/lib/polling.test.ts` (3 new); an unscaled helper fails 2 of them and a 30 s helper 3.
+- **`v2-mcp-mount-map`'s run-transport leg identifies its own run.** It diffed `listRuns` around one `tools/call` and required exactly one new `conformance-noop` run, but the suite runs files concurrently and that fixture is every file's smallest run: the v2 reference host's CI (4 workers) failed "got 2 new run(s)" on a host whose `tools/call` started exactly one, and `fresh[0]` could have been a sibling's run read for the wrong transport. The leg now requires at least one new run and reads the transport of the run the result names (when `listRuns` shows it), else the only new run, else passes if any new run in the window started `mcp`.
+- **`spec/v2/core/webhooks.md`'s `Stable` banner cites RFC 0217**, now `Accepted` on the v2 reference host's certified 2.42.0 cut. No scenario change.
+
 ## [2.42.0] — 2026-09-26 — `replay_context_summary_unavailable` is a registered code, and an unregistered subscription has no sink
 
 - **RFC 0217: after unregister, the dead-letter read answers `404 not_found`, as for a subscription that never existed.** `v2-webhook-durable-delivery` gains `openwop.requirement.0217.dead-letter-read-after-unregister`, gated on `webhooks.deadLetter`: read the sink (`200`, the control), unregister (`204`), read again, and read a never-minted same-tenant id; both later reads must be `404 not_found`. Closes RFC 0215's gap G5. Sabotage: a v2 reference host whose read answers `200 { deliveries: [] }` for an unknown id fails the row.

package/README.md

@@ -11,7 +11,7 @@
 # --legacy-peer-deps is REQUIRED, not optional: the exact peer pin is what npm's
 # default resolver refuses. npm 10.9 fails outright with
 # "Cannot read properties of null (reading 'edgesOut')" — use npm >= 11.
-npm install --legacy-peer-deps @openwop/openwop-conformance@2.42.0 @openwop/spec-artifacts@2.42.0
+npm install --legacy-peer-deps @openwop/openwop-conformance@2.42.1 @openwop/spec-artifacts@2.42.1
 # or run without install:
 npx @openwop/openwop-conformance --base-url https://api.example.com --api-key hk_test_...
 ```

package/dist/spec-artifacts.lock.json

@@ -1,5 +1,5 @@
 {
   "package": "@openwop/spec-artifacts",
-  "version": "2.42.0",
-  "stampSha256": "99ce95950e5c5c127286091e76b7569eeb6eb05ec752c853b23eb548c0a755f9"
+  "version": "2.42.1",
+  "stampSha256": "f71d4bdee95ce4bb80f65ffb6ace46bc5fb62db3456131531ad31caa1040c944"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openwop/openwop-conformance",
-  "version": "2.42.0",
+  "version": "2.42.1",
   "description": "Production-ready black-box conformance suite for OpenWOP v1.0 compliant servers.",
   "repository": {
     "type": "git",
@@ -56,6 +56,6 @@
     "@openwop/spec-artifacts": "file:../spec-artifacts"
   },
   "peerDependencies": {
-    "@openwop/spec-artifacts": "2.42.0"
+    "@openwop/spec-artifacts": "2.42.1"
   }
 }

package/requirements.json

@@ -30273,14 +30273,15 @@
         },
         {
           "section": "interop-map.json mcp.methods tools/call; runs.md run.started",
-          "requirement": "the run starts with run.started.transport mcp"
+          "requirement": null,
+          "interpolated": true
         }
       ]
     },
     {
       "id": "openwop.it.v2-mcp-mount-map.a-suspending-tool-answers-inputrequiredresult-the-retry-resolves-it-requeststate",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 181,
+      "line": 197,
       "title": "a suspending tool answers InputRequiredResult; the retry resolves it; requestState is single use and forgery-proof",
       "explicitId": null,
       "citations": [
@@ -30322,7 +30323,7 @@
     {
       "id": "openwop.it.v2-mcp-mount-map.the-mrtr-input-request-key-is-the-open-interrupt-s-interruptid-never-the-node-it",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 206,
+      "line": 222,
       "title": "the MRTR input-request key is the open interrupt’s interruptId, never the node it suspended on",
       "explicitId": null,
       "citations": [
@@ -30361,7 +30362,7 @@
     {
       "id": "openwop.it.v2-mcp-mount-map.a-list-that-differs-per-caller-is-cachescope-private",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 244,
+      "line": 260,
       "title": "a list that differs per caller is cacheScope private",
       "explicitId": null,
       "citations": [
@@ -30379,7 +30380,7 @@
     {
       "id": "openwop.it.v2-mcp-mount-map.unknown-meta-extension-keys-and-capabilities-extensions-are-opaque-processed-nor",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 261,
+      "line": 277,
       "title": "unknown _meta extension keys and capabilities.extensions are opaque: processed normally, granting nothing",
       "explicitId": null,
       "citations": [
@@ -30397,7 +30398,7 @@
     {
       "id": "openwop.it.v2-mcp-mount-map.an-unauthenticated-request-is-refused-at-the-boundary-unless-anonymousactor-is-a",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 270,
+      "line": 286,
       "title": "an unauthenticated request is refused at the boundary unless anonymousActor is advertised",
       "explicitId": null,
       "citations": [
@@ -30420,7 +30421,7 @@
     {
       "id": "openwop.it.v2-mcp-mount-map.a-credential-interrupt-is-answered-in-url-mode-url-connecturl-iserror-without-ur",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 287,
+      "line": 303,
       "title": "a credential interrupt is answered in URL mode (url = connectUrl), isError without URL support, and input_required again on an accept retry with no credential",
       "explicitId": "openwop.requirement.0199.mcp-url-mode",
       "citations": [
@@ -30458,7 +30459,7 @@
     {
       "id": "openwop.it.v2-mcp-mount-map.form-mode-is-never-emitted-for-a-nested-schema-or-a-sensitive-format-password-fi",
       "file": "v2-mcp-mount-map.test.ts",
-      "line": 328,
+      "line": 344,
       "title": "form mode is never emitted for a nested schema or a sensitive (format password) field",
       "explicitId": "openwop.requirement.0199.form-mode-no-secret",
       "citations": [

package/schemas/CORPUS-STAMP.json

@@ -1,17 +1,17 @@
 {
   "_comment": "Provenance of @openwop/spec-artifacts (RFC 0168 §D.2). files: SHA-256 per file; the conformance suite compares the installed peer against dist/spec-artifacts.lock.json at start.",
   "package": "@openwop/spec-artifacts",
-  "version": "2.42.0",
-  "corpusTag": "v2.42.0",
+  "version": "2.42.1",
+  "corpusTag": "v2.42.1",
   "files": {
     "api/.redocly.lint-ignore.yaml": "bf5a8350b88a72fa43f59605ed8d903ed24b6cfccda5e45509c9f6ed9ee4e712",
     "api/asyncapi.yaml": "d5ecb9ee6114582be3b1f662c84bfac9ae96dae7bacb853e461168f70a8e1c7d",
     "api/grpc/openwop.proto": "c3e72bb17cba514ee98feb6434e6c9b6ea6795bfd086489ec69fd882dd1ad977",
     "api/openapi.yaml": "6366b5514be71098e9ea41fc81ff52bc39db1a547b353c0b344cc2a2bf5370aa",
     "api/redocly.yaml": "b0604c89b2ca6d5076ec25725c539dad44a741a811fe524439ee6daef8baa09f",
-    "api/seams-v2.yaml": "78bc7bc551f7c91c5b8074dbb6050ab74ec39e032833c51a065c2f834f20826c",
-    "api/v2/asyncapi.yaml": "677ca1a062a22dfec6efbc5e109a2b0b356e9ee9508b638a85033361dae7a927",
-    "api/v2/openapi.yaml": "bd025e0d7ac058148e17925bb824f00dda4084063b612d6be546c221c393af95",
+    "api/seams-v2.yaml": "849b6c3d37336132343468e553b413a61a133fbc943d21ffc8e961948284db9f",
+    "api/v2/asyncapi.yaml": "96bac052de733a0987c35b4834341d91633381ff2ae1e6087ddb2956ac1edad9",
+    "api/v2/openapi.yaml": "eb39b2957737fc0f2e3187c33aac2f1475a3d2aa382a5c57686a1a15a5b643d4",
     "api/v2/redocly.yaml": "1e66b60e6118ad11a823bb620678be464d99dfe50a40e3e6f93ec9429b88b34c",
     "schemas/README.md": "0c0b737ffcf8f30e7d2809cec8a498232de710f41443212922ad8337cdde0b51",
     "schemas/a2a-task-state.schema.json": "75d5049dea8bd873ff0e7546f1c60c8d36c219bec7084264360be54a8be30ae1",
@@ -204,7 +204,7 @@
     "schemas/workspace-file.schema.json": "464de85c2a068243084ee9c1d969bc7cd5d8f7948574e58450d6493c38a0e1e4",
     "spec/v1/alias-detectors.json": "2401fcb1c18cdd688c018b3d716ae6bca85c5e356220ee2b793bd9d81872412d",
     "spec/v1/capability-declaration-classes.json": "e7729aed5c4b4e1dd02abab0530f14cc95f5d4070fe51fb139e7f5cccefa00c6",
-    "spec/v1/core-standard-manifest.json": "da8798e334fbbdc2078e4f83cab486c9f6c5c3cc32c2297d9e5a85eda15a04ad",
+    "spec/v1/core-standard-manifest.json": "bbcefda69bffa9fb67803c48ddc7e786866c655d8af36f73fc0e3b27e69a1917",
     "spec/v1/deprecations.json": "2d03f4729810280147ea08c630ea65434f2dc5370567d0aac41c3595f8337d40",
     "spec/v1/deprecations.schema.json": "3e393c405d2a41b467d8c5e3c468549078df1ce6a6d2588fc488097b95d9b55b",
     "spec/v1/event-codemap.json": "3da60d884157793a360da532a9fcbbfb5285636db325a74cec94b34622186d97",
@@ -240,7 +240,7 @@
     "spec/v2/core/security-defaults.md": "500471a8db7af9b776ac40b4a9a278c9f3d45e1c1dead880114e7fadc7bee37d",
     "spec/v2/core/tool-catalog.md": "35f1a3fd509db0fc0490ddf400686fe94dc4b20c98064d5ebe776da516153e60",
     "spec/v2/core/versioning.md": "0aded71d090c8358c3ce17763c120cfc1cc42531a5eaa1b8a2a7016ed9594069",
-    "spec/v2/core/webhooks.md": "221fc8f3222c34ee094723602f286f1b2acad7931188cad6c3611189c9c6acbb",
+    "spec/v2/core/webhooks.md": "78d7e237866bf1ee95bbfa9d5b62b619ca2f8ec677d1b752ba96ed5efcfc77ef",
     "spec/v2/core/workflow-chain-packs.md": "ee45d3fede3bb6f0cc6abcf0d6c929c7cd213a0fbe862b738a998f929c4d1102",
     "spec/v2/corrections.json": "cc74ffde74384b0f261a4f625871d922e8661d654d647a8534e21036595cb280",
     "spec/v2/corrections.schema.json": "4ac595b9a6d7f66d53de03fe0edbe0dc58de46426932387bfdc0ceb3cf949a3e",
@@ -294,9 +294,9 @@
     "spec/v2/path-manifest.json": "ae9b56d03a701061fd48ad0b73cb0373493f6a4547da92763b422295b5e19535",
     "spec/v2/peer-dependency-aliases.json": "d10299280abee08258502925bc327293ee413e0108cd6e6ec75ff6110653308d",
     "spec/v2/profiles.json": "0636f19fceae625390003a347e70ef4797d84766b5c24ce8a02cea52aadebca4",
-    "spec/v2/release.json": "b2fb154e00b0aeb9a64c29d56d99fbd21b9de1872e9a047c81f6c1ee7c50a74c",
+    "spec/v2/release.json": "c226854124edd701082c57b55c908cdf09926837611a59d00e306696a06a9b8a",
     "spec/v2/retention-floors.json": "eaf3722d95c79947af1d4269ef85117e126518c588cfcf1a2b21b97269f51624",
-    "spec/v2/surface-baseline.json": "fbf584bd7cb6905f0f8280d7d7ae6746fd30f948dc08b4f80aac0afc760f22ce"
+    "spec/v2/surface-baseline.json": "8411f06cd9888524b6d234e8d111896d8c90d06991453c9a192e7550d0b3cb9e"
   },
-  "corpusCommit": "bb35ff0f896edfbc7300c5c71e4e33a678e7f815"
+  "corpusCommit": "c92bac3ebafda0fab5a6113df67422efe428d70d"
 }

package/src/lib/polling.ts

@@ -71,6 +71,27 @@ export function scaledTimeoutMs(timeoutMs: number): number {
   return scale === 1 ? timeoutMs : Math.ceil(timeoutMs * scale);
 }
 
+/**
+ * Live-model scenarios (RFC 0111's `conformance-context-budget-live`) drive real
+ * model turns and child runs; one run takes 30–40 s on a production host
+ * (MyndHyve, 2026-09-26), so vitest's global 30 s `testTimeout` killed them
+ * before any assertion — a suite defect that looks like a host failure.
+ *
+ * `LIVE_RUN_POLL_MS` is the base bound for ONE live run to reach a terminal
+ * status (below the fixture's own `settings.timeout` of 300 s); pass it as
+ * `pollUntilTerminal(runId, { timeoutMs: LIVE_RUN_POLL_MS })` — `pollUntil`
+ * scales it. `liveScenarioTimeoutMs(runs)` is the per-test vitest timeout: the
+ * scaled sum of the scenario's poll bounds plus 60 s for its seam reads, so the
+ * poll deadline always fires first and a hung host fails with a named poll
+ * message, never a bare vitest timeout. Both scale with
+ * `OPENWOP_POLL_TIMEOUT_SCALE`, so their order holds at every scale.
+ */
+export const LIVE_RUN_POLL_MS = 180_000;
+
+export function liveScenarioTimeoutMs(runs: number): number {
+  return scaledTimeoutMs(runs * LIVE_RUN_POLL_MS + 60_000);
+}
+
 const TERMINAL = new Set(['completed', 'failed', 'cancelled']);
 
 export async function getRun(runId: string): Promise<RunSnapshot> {

package/src/scenarios/context-budget-transcript-bound.test.ts

@@ -55,7 +55,7 @@
 
 import { describe, it, expect } from 'vitest';
 import { driver } from '../lib/driver.js';
-import { pollUntilTerminal } from '../lib/polling.js';
+import { LIVE_RUN_POLL_MS, liveScenarioTimeoutMs, pollUntilTerminal } from '../lib/polling.js';
 import { behaviorGate } from '../lib/behavior-gate.js';
 import { isFixtureAdvertised } from '../lib/fixtures.js';
 import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
@@ -111,7 +111,7 @@ describe('context-budget-transcript-bound (RFC 0111 §"Context economy")', () =>
     const runId = runIdOf(create.json);
     expect(runId, req(ID, 'RFC 0111', 'the create response MUST carry a runId')).toBeDefined();
     if (runId === undefined) return softSkip('blocked', 'no runId');
-    await pollUntilTerminal(runId);
+    await pollUntilTerminal(runId, { timeoutMs: LIVE_RUN_POLL_MS });
 
     const windows: Array<{ iteration: number; window: TranscriptWindow }> = [];
     for (let iteration = 1; iteration <= MAX_ITERATIONS_PROBED; iteration += 1) {
@@ -153,5 +153,5 @@ describe('context-budget-transcript-bound (RFC 0111 §"Context economy")', () =>
 
     if (log === null) return softSkip('blocked', 'the run event-log seam is unavailable, so the real-event, recent-tail and pressure rules were not measured');
     if (!pressure) softSkip('inapplicable', `no iteration shows budget pressure — every eligible event fit under transcriptTokenBudget ${budget}, so the bound was never exercised (a budget the run never reaches is not a witness)`);
-  });
+  }, liveScenarioTimeoutMs(1));
 });

package/src/scenarios/context-summarization-replay.test.ts

@@ -38,7 +38,7 @@
 
 import { describe, it, expect } from 'vitest';
 import { driver } from '../lib/driver.js';
-import { pollUntilTerminal } from '../lib/polling.js';
+import { LIVE_RUN_POLL_MS, liveScenarioTimeoutMs, pollUntilTerminal } from '../lib/polling.js';
 import { behaviorGate } from '../lib/behavior-gate.js';
 import { isFixtureAdvertised } from '../lib/fixtures.js';
 import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
@@ -125,7 +125,7 @@ describe('context-summarization-replay (RFC 0111 §"Replay determinism")', () =>
     const sourceRunId = runIdOf(create.json);
     expect(sourceRunId, req(ID, 'rest-endpoints.md POST /v1/runs', 'the create response MUST carry a runId')).toBeDefined();
     if (sourceRunId === undefined) return softSkip('blocked', 'no runId');
-    await pollUntilTerminal(sourceRunId);
+    await pollUntilTerminal(sourceRunId, { timeoutMs: LIVE_RUN_POLL_MS });
 
     const sourceQ = await queryTestEvents(sourceRunId);
     if (!sourceQ.ok) return softSkip('blocked', 'the run event-log seam is unavailable');
@@ -141,7 +141,7 @@ describe('context-summarization-replay (RFC 0111 §"Replay determinism")', () =>
     const forkRunId = runIdOf(fork.json);
     expect(forkRunId, req(ID, 'rest-endpoints.md POST /v1/runs/{runId}:fork', 'replay fork MUST return a runId')).toBeDefined();
     if (forkRunId === undefined) return softSkip('blocked', 'no fork runId');
-    await pollUntilTerminal(forkRunId);
+    await pollUntilTerminal(forkRunId, { timeoutMs: LIVE_RUN_POLL_MS });
 
     const forkQ = await queryTestEvents(forkRunId);
     if (!forkQ.ok) return softSkip('blocked', 'the event-log seam is unavailable for the fork');
@@ -153,5 +153,5 @@ describe('context-summarization-replay (RFC 0111 §"Replay determinism")', () =>
     if (sourceTexts === null || forkTexts === null) return softSkip('inapplicable', 'the transcript-window seam serves no entries[] for these runs, so the model-facing summary text was not compared (summaryRef reuse was)');
     expect(sourceTexts.length, req(ID, 'RFC 0111 §"Replay determinism"', 'the source run summarized, so its transcript windows MUST carry the summary text it fed')).toBeGreaterThan(0);
     expect(forkTexts, req(ID, 'RFC 0111 §"Replay determinism"', 'the replay MUST feed the model the recorded summary text, byte for byte — never a re-summarization')).toEqual(sourceTexts);
-  });
+  }, liveScenarioTimeoutMs(2));
 });

package/src/scenarios/v2-mcp-mount-map.test.ts

@@ -172,10 +172,26 @@ describe('RFC 0208 — v2-mcp-mount-map (host as MCP 2026-07-28 server, gated on
     const before = new Set(await list());
     const ok = await toolCall(m.url, 'conformance-noop');
     const fresh = (await list()).filter((x) => !before.has(x));
-    expect(fresh.length, req(R('mcp-run-transport'), 'interop-map.json mcp.methods tools/call', `tools/call MUST start a run (v2Operation createRun) that listRuns shows the same Subject (got ${fresh.length} new run(s); result ${JSON.stringify(ok.error ?? ok.result)})`)).toBe(1);
-    const poll = await driver.get(`/runs/${encodeURIComponent(fresh[0]!)}/events/poll?timeout=1`);
-    const started = ((poll.json as { events?: Array<{ type?: string; payload?: { transport?: string } }> } | undefined)?.events ?? []).find((e) => e.type === 'run.started');
-    expect(started?.payload?.transport, req(R('mcp-run-transport'), 'interop-map.json mcp.methods tools/call; runs.md run.started', 'the run starts with run.started.transport mcp')).toBe('mcp');
+    expect(fresh.length, req(R('mcp-run-transport'), 'interop-map.json mcp.methods tools/call', `tools/call MUST start a run (v2Operation createRun) that listRuns shows the same Subject (got ${fresh.length} new run(s); result ${JSON.stringify(ok.error ?? ok.result)})`)).toBeGreaterThanOrEqual(1);
+    // WHICH new run is ours (2.42.1). The leg counted `fresh.length === 1`, but
+    // the suite runs files concurrently and conformance-noop is every file's
+    // smallest run, so a sibling's run landed in the same window: the v2
+    // reference host's CI (4 workers) failed "got 2 new run(s)" on a host whose
+    // own tools/call started exactly one, and `fresh[0]` could have been the
+    // sibling's run, read for the wrong transport. Ours is the runId the result
+    // names when it names one listRuns shows, else the only new run; when the
+    // window stays ambiguous, the requirement holds if any new run started mcp.
+    const named = ((): string | null => {
+      const m = /"runId"\s*:\s*"([^"]+)"/.exec(JSON.stringify(ok.result ?? ''));
+      return m && fresh.includes(m[1]!) ? m[1]! : null;
+    })();
+    const transportOf = async (runId: string): Promise<string | undefined> => {
+      const poll = await driver.get(`/runs/${encodeURIComponent(runId)}/events/poll?timeout=1`);
+      return ((poll.json as { events?: Array<{ type?: string; payload?: { transport?: string } }> } | undefined)?.events ?? []).find((e) => e.type === 'run.started')?.payload?.transport;
+    };
+    const ours = named ?? (fresh.length === 1 ? fresh[0]! : null);
+    const transports = ours !== null ? [await transportOf(ours)] : await Promise.all(fresh.map(transportOf));
+    expect(transports.includes('mcp') ? 'mcp' : transports[0], req(R('mcp-run-transport'), 'interop-map.json mcp.methods tools/call; runs.md run.started', `the run starts with run.started.transport mcp (${ours !== null ? `run ${ours}` : `${fresh.length} runs started in the window, none named by the result`}; transports ${JSON.stringify(transports)})`)).toBe('mcp');
   });
 
   it('a suspending tool answers InputRequiredResult; the retry resolves it; requestState is single use and forgery-proof', async () => {