diff --git a/.claude/skills/pre-push-gate/SKILL.md b/.claude/skills/pre-push-gate/SKILL.md index ea8bcb64..fc151b5e 100644 --- a/.claude/skills/pre-push-gate/SKILL.md +++ b/.claude/skills/pre-push-gate/SKILL.md @@ -207,6 +207,8 @@ it — the split is the design. `npm run pack:verify` builds, packs the real tarball, installs it into a clean throwaway consumer, and drives the installed `mcp-inspector` bin end to end. It -needs **network access**, so it is a local/release check and is in neither -`local:gate` nor CI. Run it when touching packaging (the `files` allowlist, -a bundler `external` list, anything read from disk at runtime). +needs **network access**, so it is a local/release check: it is **not** a +`local:gate` stage, and CI runs it only in the `publish` job on a published +GitHub Release — never on a push or PR. Run it when touching packaging (the +`files` allowlist, a bundler `external` list, anything read from disk at +runtime), and as its own step when cutting a release (the `release` skill). diff --git a/.claude/skills/release/SKILL.md b/.claude/skills/release/SKILL.md index ee526531..d409acb5 100644 --- a/.claude/skills/release/SKILL.md +++ b/.claude/skills/release/SKILL.md @@ -36,7 +36,7 @@ other. | Branch | `v2/chore/-bump-`, cut from `origin/v2/main` | the milestone-merge branch, cut from `origin/main` | | Base | **`v2/main`** | **`main`** | | Carries | the `npm audit` report, **any fixes the audit forces**, and the **version bump** — all three, one PR | the milestone's work, arriving whole from `v2/main`. **No commits of its own.** | -| Verified by | `npm run local:gate` | `npm run local:gate` **plus** a hand-driven smoke of every contribution in the milestone, from the **production build**, written up as a **ledger artifact** | +| Verified by | `npm run local:gate` | `npm run local:gate`, **plus** `npm run pack:verify` (not a gate stage), **plus** a hand-driven smoke of every contribution in the milestone, from the **production build**, written up as a **ledger artifact** | | Merged when | reviewed and green | the ledger is reviewed by the maintainers and clean | Then, and only then, a maintainer tags and publishes the **GitHub Release** @@ -143,9 +143,16 @@ Then drive it. Work from a **dedicated worktree** with its own full `npm install` (a symlinked `node_modules` passes lint and tests and then fails every story file), run `npm run local:gate` there, and exercise the app from the **production build** — the packaged bin and the built bundles, not `vite dev`. -The `local-dev`, `test-servers` and `pre-push-gate` skills cover the mechanics; -`pack:verify` inside the gate is what proves the tarball a consumer installs -actually resolves. +The `local-dev`, `test-servers` and `pre-push-gate` skills cover the mechanics. + +**Then run `npm run pack:verify` there as its own step.** It is what proves the +tarball a consumer installs actually resolves, and ⚠️ **`local:gate` does not +run it** — `local:gate:stages` has no packaging stage, and a green gate says +nothing about the published tarball (#2380). CI runs it only in the `publish` +job, which fires on the published GitHub Release — after the tag exists — so +skipping it here means the first signal of a broken package arrives too late to +stop the release. It needs network access; record its result (tarball size and +the `pack:verify OK` line) for the ledger below. **Every contribution closed in the milestone gets driven, not read.** The bar is observed behavior from the running app — a rendered panel, a status attribute, a @@ -165,11 +172,13 @@ and link it from PR 2. Shape it like the standfirst saying what tree was tested and that its hash matches `origin/v2/main`, plus whether the milestone payload is complete (the only issue left open should be the merge itself). -- **Verdict band** — `local:gate` result, milestone issues verified as `N / N`, - distinct test count, regressions found. -- **The automated gate** — one cell per stage with its number (file counts, - test counts, smoke count, `pack:verify` size), and a note on what is new this +- **Verdict band** — `local:gate` and `pack:verify` results, milestone issues + verified as `N / N`, distinct test count, regressions found. +- **The automated gate** — one cell per `local:gate` stage with its number + (file counts, test counts, smoke count), and a note on what is new this milestone. +- **The packaging check** — `pack:verify` in its own cell, apart from the gate + stages because it is not one of them: its result and the tarball size. - **One section per theme**, each a table of *Issue · What was driven · Observed · Status*. One row per closed issue, issue-linked, with the actual output in the Observed cell. diff --git a/clients/web/package-lock.json b/clients/web/package-lock.json index 9af37724..c666dc79 100644 --- a/clients/web/package-lock.json +++ b/clients/web/package-lock.json @@ -46,7 +46,7 @@ "eslint-plugin-react-hooks": "^7.1.1", "eslint-plugin-react-refresh": "^0.5.2", "eslint-plugin-storybook": "^10.5.5", - "happy-dom": "^20.9.0", + "happy-dom": "^20.11.2", "playwright": "^1.58.2", "storybook": "^10.5.5", "tsup": "^8.5.1", @@ -5264,9 +5264,9 @@ "optional": true }, "node_modules/happy-dom": { - "version": "20.11.1", - "resolved": "https://registry.npmjs.org/happy-dom/-/happy-dom-20.11.1.tgz", - "integrity": "sha512-XSt8tMzbW9ymE7687xztkO1ckR7qJNQ3LywY9vlYGhGi3zXrGBHuUo2Cl1ztZaICW+1eAGdkLbj6iwVqDT33kg==", + "version": "20.14.5", + "resolved": "https://registry.npmjs.org/happy-dom/-/happy-dom-20.14.5.tgz", + "integrity": "sha512-x/RzkpWO40bTjIoT30iQtt64FLLmH/iRcUCN2X//bLx7H3ifkdfPXyqsro/OYtqzIAhiLMMA7mmiOR9C3NOKjQ==", "dev": true, "license": "MIT", "dependencies": { diff --git a/clients/web/package.json b/clients/web/package.json index 421c8b99..4c8cb795 100644 --- a/clients/web/package.json +++ b/clients/web/package.json @@ -70,7 +70,7 @@ "eslint-plugin-react-hooks": "^7.1.1", "eslint-plugin-react-refresh": "^0.5.2", "eslint-plugin-storybook": "^10.5.5", - "happy-dom": "^20.9.0", + "happy-dom": "^20.11.2", "playwright": "^1.58.2", "storybook": "^10.5.5", "tsup": "^8.5.1", diff --git a/clients/web/src/components/elements/AppRenderer/AppRenderer.test.tsx b/clients/web/src/components/elements/AppRenderer/AppRenderer.test.tsx index b6efc1ed..1dd1660e 100644 --- a/clients/web/src/components/elements/AppRenderer/AppRenderer.test.tsx +++ b/clients/web/src/components/elements/AppRenderer/AppRenderer.test.tsx @@ -1,5 +1,5 @@ import { createRef, StrictMode } from "react"; -import { act, waitFor } from "@testing-library/react"; +import { act } from "@testing-library/react"; import { describe, it, expect, vi, beforeEach, afterEach } from "vitest"; import type { AppBridge } from "@modelcontextprotocol/ext-apps/app-bridge"; import type { CallToolResult, Tool } from "@modelcontextprotocol/client"; @@ -79,6 +79,34 @@ async function flushAsync(): Promise { }); } +// Runs `mutate` and resolves once every MutationObserver that was already +// watching `data-mantine-color-scheme` on `documentElement` has had its +// callback delivered — which is what the AppRenderer theme push rides on. +// +// This is an awaited condition rather than a wall-clock budget, per #2384. +// A probe observer registered *after* the component's is notified after it: +// observers are queued in registration order and each delivery is an ordinary +// microtask, so by the time the probe's callback runs the component's has +// already run and the assertion below is settled. No polling and no timeout is +// involved, so nothing here is load-sensitive. +async function flipThemeAttributeAndAwaitObservers( + value: string, +): Promise { + await act(async () => { + await new Promise((resolve) => { + const probe = new MutationObserver(() => { + probe.disconnect(); + resolve(); + }); + probe.observe(document.documentElement, { + attributes: true, + attributeFilter: ["data-mantine-color-scheme"], + }); + document.documentElement.setAttribute("data-mantine-color-scheme", value); + }); + }); +} + describe("AppRenderer", () => { it("renders an iframe with the sandbox path and tool title", () => { const bridge = createMockBridge(); @@ -538,47 +566,17 @@ describe("AppRenderer", () => { // flip we trigger below. bridge.sendHostContextChange.mockClear(); - await act(async () => { - document.documentElement.setAttribute( - "data-mantine-color-scheme", - "dark", - ); - // MutationObserver callbacks are delivered on a microtask. - await Promise.resolve(); - }); - // `waitFor`, not a bare assertion after the single microtask above: how - // many ticks happy-dom takes to deliver the MutationObserver callback is - // load-dependent, so under a full parallel run the observer can still be - // pending here. Observed failing exactly once that way, with 0 calls. - // - // The default 1000ms then turned out not to be enough either — it failed - // twice in a row in `npm run local:gate` (at ~1021ms, still 0 calls) while - // passing every time this file runs alone, which is the signature of a - // budget that is too tight rather than of a broken observer. Raised - // rather than retried: a `waitFor` that is generous costs nothing on the - // passing path, since it returns as soon as the assertion holds. - // - // #2323 briefly deleted this argument as one of its "a budget inside an - // equal budget can never be observed" cases, which it was: 5000 inside a - // 5000ms test could never win. That is fixed from the other end now — the - // enclosing budget is 15000 — so the raise is observable again and has to - // stay, because the value it beats is a measured failure rather than a - // default. It does NOT ride on `asyncUtilTimeout`, which is pinned at - // 1000 precisely because raising it globally was measured worse - // (Copilot). - await waitFor( - () => - expect(bridge.sendHostContextChange).toHaveBeenCalledWith( - expect.objectContaining({ - theme: "dark", - styles: expect.objectContaining({ - variables: expect.objectContaining({ - "--color-background-primary": "#101113", - }), - }), + await flipThemeAttributeAndAwaitObservers("dark"); + + expect(bridge.sendHostContextChange).toHaveBeenCalledWith( + expect.objectContaining({ + theme: "dark", + styles: expect.objectContaining({ + variables: expect.objectContaining({ + "--color-background-primary": "#101113", }), - ), - { timeout: 5000 }, + }), + }), ); } finally { getComputedStyleSpy.mockRestore(); @@ -599,13 +597,10 @@ describe("AppRenderer", () => { // No `initialized` emitted — the theme observer is gated, like the // container and displayMode pushes, so a pre-handshake flip is dropped. bridge.sendHostContextChange.mockClear(); - await act(async () => { - document.documentElement.setAttribute( - "data-mantine-color-scheme", - "dark", - ); - await Promise.resolve(); - }); + // Same awaited-delivery helper as the positive case: it is what makes this + // "not called" a real gate rather than a vacuous pass on a flip that was + // never delivered at all. + await flipThemeAttributeAndAwaitObservers("dark"); expect(bridge.sendHostContextChange).not.toHaveBeenCalled(); document.documentElement.removeAttribute("data-mantine-color-scheme"); }); @@ -627,13 +622,10 @@ describe("AppRenderer", () => { }); bridge.sendHostContextChange.mockClear(); - await act(async () => { - document.documentElement.setAttribute( - "data-mantine-color-scheme", - "dark", - ); - await Promise.resolve(); - }); + // Same awaited-delivery helper as the positive case: it is what makes this + // "not called" a real gate rather than a vacuous pass on a flip that was + // never delivered at all. + await flipThemeAttributeAndAwaitObservers("dark"); expect(bridge.sendHostContextChange).not.toHaveBeenCalled(); document.documentElement.removeAttribute("data-mantine-color-scheme"); });