test: full test-suite refactor sweep (#61)

* chore(test): start test-suite refactor sweep

* test(ltl): pin exact multi-obligation residual AST

* test(ltl): table-test finalize Kleene connective combinations

* test(ltl): pin reduce over pending inner for bound, Or, Not

* test(ltl): marshal bounded Always steps/duration/deadline

* test(verifier): cover LTL combinator verdict transitions and within unit panic

* test(verifier): table-test DecodeAction kinds and lastAction field exposure

* test(verifier): assert WithPlatform(ios) reaches the picker host and key pool

* test(verifier): widen weighted-selection assertion to a 5x skew margin

* test(verifier): un-skip ax-find round trip with a committed tree fixture

* test(runner): pin isWDADrop to sidecar reconnect-failed message origin

* test(runner): assert PressKey/Wait trace encoding records kind-specific fields

* test(runner): cover RenderSummary unsupported-verbs surfacing branch

* test(trace): set Hierarchy in round-trip and lock lossy Tree contract

Also add a -race concurrent WriteStep test that asserts N well-formed JSONL lines, catching torn lines if the writer mutex is dropped.

* test(trace): round-trip witnesses/changes/metrics/exceptions, pin step-0 witness

* test(trace): document ViolationsAreGreppable grep contract and lock-free WriteScreenshot

* test(hierarchy): cover invalid-JSON and malformed-bounds parser paths

* test(trace): guard writer mutex via WriteStep/Close race on w.file

* test(replay): drop unfailable assets and devproxy assertions

* test(replay): cache reuses on equal mtime, reparses after append

* test(replay): violation marker falls back to detection step when attributed missing

* test(replay): corrupt meta/trace dirs return 500 with error body

* test(replay): SSE client receives runs.changed after a broadcast

* test(replay): Run coalesces creates, ignores write/chmod, closes subs on cancel

* fix(sidecar): synchronize health fixture writes and exercise healthError

* test(sidecar): cover swipe/longpress/doubletap/erase/presskey/metrics/logs translations

* test(sidecar): cover DoubleTapSelector composition and mid-gesture cancel

* test(sidecar): assert gRPC error status surfaces from action RPC

* fix(chrome): route action methods through runCtx so caller cancellation aborts CDP

* fix(chrome): route hierarchy/screenshot/waitidle/metrics through runCtx

* refactor(ios): extract pure simctl JSON parsers

* refactor(ios): add command-runner seams for EnsureSimulator

* test(ios): table-test simctl parsers and EnsureSimulator seams

* test(sidecarassets): cover placeholder build path

* test(sidecarassets): assert reuse via sentinel bytes not mtime

* test(bundler): cover properties-only spec registration

* refactor(testrun): extract prepareBundleInputs from Execute

* test(testrun): cover prepareBundleInputs aliases and missing-runtime error

* test(testrun): table-test resolveRuntimeSibling search edges

* test(testrun): exact-output tests for progressHandler line format

* fix(cmd): point bundle-check aliases at pkg/spec/src

* test(cmd): smoke-test bundle-check resolves spec aliases

* test(cmd): table-test hier-check parse and FindAll on fixture

* test(cmd): unit-test buildBrowseURL deep-link vs root

* test(cmd): drop flaky TestRun_Doctor that launched real Chromium

* test(cmd): pin pipeline error to bundle resolution on web platform

* test(replay-ui): add bun test script

* ci(replay-ui): run bun test via make web-test target

* ci(replay-ui): point bun cache key at replay-ui/bun.lock

* test(replay-ui): exercise real URL encoding and non-ok throw in getJson

* refactor(replay-ui): extract snapshot flatten/getAtPath into lib module

* test(replay-ui): pin snapshot flatten/getAtPath path round-trip

* refactor(replay-ui): extract action selector/format into lib module

* test(replay-ui): pin action selector parse and row formatting

* refactor(replay-ui): share one statusFor between panels

* refactor(replay-ui): extract run-history derivation into lib module

* test(replay-ui): pin shared statusFor precedence and ordering

* test(replay-ui): pin run-history derivation alignment

* refactor(replay-ui): export clampIndex for testing

* refactor(replay-ui): extract keyboard-nav dispatch into pure module

* refactor(replay-ui): extract metrics formatters into lib module

* test(replay-ui): pin clampIndex step boundaries

* test(replay-ui): pin keyboard-nav ownership and key routing

* test(replay-ui): pin metrics formatters and path gap handling

* refactor(sidecar): expose device-output parsers as internal for testing

* test(sidecar): table-test device-output parsers against malformed input

* test(sidecar): cover logcat parsing year inference and line skipping

* test(sidecar): pin pressKey keycode mapping and unknown-key rejection

* test(sidecar): metrics bundleId falls back to launched app and honors override

* test(sidecar): loosen deadline upper bound to tolerate slow CI scheduling

* test(web-runtime): export selector builders for unit tests

* test(web-runtime): guard sanitize cycle, function, and depth limits

* test(web-runtime): table-test selector builder quoting and escaping

* test(sidecar): collapse scalar-forwarding RPC tests into a table

* test(replay-ui): dedup step/summary fixtures into shared module

* test(ios): collapse pickSimulator point-tests into a table
This commit is contained in:
pj authored and GitHub committed 2026-06-06 13:59:08 +05:30
1 parent 410602d2e1
commit 94d9511312
66 files changed
+3419 -606

No files matched your search

@@ -0,0 +1,74 @@
import { describe, it, expect } from "bun:test";
import {
formatActionRow,
formatElapsed,
parseSelector,
tagFromSelector,
} from "../lib/action-format";
import { summary } from "./fixtures";
// Bug class: selector parsing mislabels every action row — splitting on the
// wrong colon, treating a value-with-colon as the kind, or dropping the prefix
// ellipsis would render the wrong target tag for every step.
describe("parseSelector", () => {
const cases: { input: string; out: ReturnType<typeof parseSelector> }[] = [
{ input: "id:login", out: { kind: "id", value: "login" } },
{ input: "text:Sign In", out: { kind: "text", value: "Sign In" } },
{ input: "textPrefix:Hello", out: { kind: "textPrefix", value: "Hello" } },
{ input: "id:com.app:id/btn", out: { kind: "id", value: "com.app:id/btn" } },
{ input: "bogus:x", out: null },
{ input: ":leading", out: null },
{ input: "no-colon", out: null },
];
for (const { input, out } of cases) {
it(`parses ${input}`, () => {
expect(parseSelector(input)).toEqual(out);
});
}
});
describe("tagFromSelector", () => {
it("appends ellipsis only for prefix selectors", () => {
expect(tagFromSelector("textPrefix:Hel")).toBe("Hel...");
expect(tagFromSelector("text:Hello")).toBe("Hello");
expect(tagFromSelector("plain")).toBe("plain");
});
});
describe("formatActionRow", () => {
it("observes when no action kind, with and without screen", () => {
expect(formatActionRow(summary({}))).toEqual({
verb: "Observe",
target: "",
targetIsTag: false,
});
expect(formatActionRow(summary({ screen: "Home" }))).toEqual({
verb: "Observe",
target: "@ Home",
targetIsTag: false,
});
});
it("treats a selector label as a tag and a coordinate label as literal", () => {
expect(
formatActionRow(summary({ action_kind: "Tap", action_label: "id:btn" })),
).toEqual({ verb: "Click", target: "btn", targetIsTag: true });
expect(
formatActionRow(summary({ action_kind: "Tap", action_label: "(10, 20)" })),
).toEqual({ verb: "Click", target: "(10, 20)", targetIsTag: false });
});
it("maps known verbs and falls back to the raw kind", () => {
expect(formatActionRow(summary({ action_kind: "InputText", action_label: "hi" })).verb).toBe("Type");
expect(formatActionRow(summary({ action_kind: "Swipe" })).verb).toBe("Swipe");
expect(formatActionRow(summary({ action_kind: "Custom" })).verb).toBe("Custom");
});
});
describe("formatElapsed", () => {
it("formats mm:ss.mmm and clamps negatives to zero", () => {
expect(formatElapsed(0)).toBe("00:00.000");
expect(formatElapsed(65_432)).toBe("01:05.432");
expect(formatElapsed(-50)).toBe("00:00.000");
});
});
+31 -4
View File
@@ -1,10 +1,37 @@
import { describe, it, expect } from "bun:test";
import { screenshotUrl } from "../api";
import { getJson, screenshotUrl } from "../api";
describe("screenshotUrl", () => {
it("encodes runId and name", () => {
expect(screenshotUrl("run-1", "step-00001.png")).toBe(
"/api/runs/run-1/screenshots/step-00001.png",
it("percent-encodes runId and name with reserved characters", () => {
expect(screenshotUrl("run #1/a", "step 00001.png")).toBe(
"/api/runs/run%20%231%2Fa/screenshots/step%2000001.png",
);
});
});
describe("getJson", () => {
it("returns the decoded body on a 200 response", async () => {
const server = Bun.serve({
port: 0,
fetch: () => Response.json({ ok: true }),
});
try {
const body = await getJson<{ ok: boolean }>(server.url.href);
expect(body).toEqual({ ok: true });
} finally {
server.stop(true);
}
});
it("throws on a non-ok response instead of returning the error body", async () => {
const server = Bun.serve({
port: 0,
fetch: () => new Response("boom", { status: 500 }),
});
try {
await expect(getJson(server.url.href)).rejects.toThrow("500");
} finally {
server.stop(true);
}
});
});
+15
View File
@@ -0,0 +1,15 @@
import type { Step, StepSummary } from "../types";
export function step(over: Partial<Step>): Step {
return { step: 0, timestamp: "1970-01-01T00:00:00.000Z", ...over };
}
export function summary(over: Partial<StepSummary>): StepSummary {
return {
index: 0,
timestamp: "1970-01-01T00:00:00.000Z",
has_violations: false,
has_exceptions: false,
...over,
};
}
@@ -0,0 +1,103 @@
import { describe, it, expect } from "bun:test";
import {
dispatchKey,
targetOwnsArrowKeys,
type KeyboardNavOptions,
} from "../lib/keyboard-nav";
function el(
over: Partial<{
tagName: string;
isContentEditable: boolean;
role: string | null;
parent: HTMLElement | null;
}> = {},
): HTMLElement {
const role = over.role ?? null;
return {
tagName: over.tagName ?? "DIV",
isContentEditable: over.isContentEditable ?? false,
getAttribute: (name: string) => (name === "role" ? role : null),
parentElement: over.parent ?? null,
} as unknown as HTMLElement;
}
function spyOptions() {
const calls: string[] = [];
const make = (name: keyof KeyboardNavOptions) => () => {
calls.push(name);
};
const options: KeyboardNavOptions = {
onPrev: make("onPrev"),
onNext: make("onNext"),
onJumpStart: make("onJumpStart"),
onJumpEnd: make("onJumpEnd"),
onJumpPrev10: make("onJumpPrev10"),
onJumpNext10: make("onJumpNext10"),
onJumpNextViolation: make("onJumpNextViolation"),
};
return { calls, options };
}
describe("targetOwnsArrowKeys", () => {
it("walks ancestors and matches arrow-owning roles", () => {
expect(targetOwnsArrowKeys(el({ role: "option" }))).toBe(true);
const child = el({ role: null, parent: el({ role: "listbox" }) });
expect(targetOwnsArrowKeys(child)).toBe(true);
expect(targetOwnsArrowKeys(el({ role: "banner" }))).toBe(false);
expect(targetOwnsArrowKeys(null)).toBe(false);
});
});
// Bug class: navigation keys firing while the user types in a form field would
// scrub the timeline out from under them; and arrow keys must yield to a
// listbox/tab that owns them so its own roving focus still works.
describe("dispatchKey ownership", () => {
it("ignores keys originating in editable targets", () => {
const { calls, options } = spyOptions();
expect(dispatchKey({ key: "j", target: el({ tagName: "INPUT" }) }, options)).toBe(false);
expect(dispatchKey({ key: "g", target: el({ isContentEditable: true }) }, options)).toBe(false);
expect(calls).toEqual([]);
});
it("yields arrow keys to an owning ancestor but still handles letters", () => {
const { calls, options } = spyOptions();
const inListbox = el({ parent: el({ role: "listbox" }) });
expect(dispatchKey({ key: "ArrowRight", target: inListbox }, options)).toBe(false);
expect(dispatchKey({ key: "j", target: inListbox }, options)).toBe(true);
expect(calls).toEqual(["onNext"]);
});
it("ignores keys combined with a modifier", () => {
const { calls, options } = spyOptions();
expect(dispatchKey({ key: "j", metaKey: true }, options)).toBe(false);
expect(dispatchKey({ key: "j", ctrlKey: true }, options)).toBe(false);
expect(calls).toEqual([]);
});
});
describe("dispatchKey routing", () => {
const cases: [string, boolean, keyof KeyboardNavOptions][] = [
["ArrowLeft", false, "onPrev"],
["k", false, "onPrev"],
["ArrowLeft", true, "onJumpPrev10"],
["ArrowRight", false, "onNext"],
["j", true, "onJumpNext10"],
["g", false, "onJumpStart"],
["G", false, "onJumpEnd"],
[".", false, "onJumpNextViolation"],
];
for (const [key, shiftKey, expected] of cases) {
it(`${shiftKey ? "shift+" : ""}${key} -> ${expected}`, () => {
const { calls, options } = spyOptions();
expect(dispatchKey({ key, shiftKey }, options)).toBe(true);
expect(calls).toEqual([expected]);
});
}
it("leaves unmapped keys untouched", () => {
const { calls, options } = spyOptions();
expect(dispatchKey({ key: "x" }, options)).toBe(false);
expect(calls).toEqual([]);
});
});
@@ -0,0 +1,63 @@
import { describe, it, expect } from "bun:test";
import {
buildPath,
formatHeap,
formatTime,
fractionFor,
} from "../lib/metrics-format";
describe("formatHeap", () => {
const cases: [number, string][] = [
[0, "0B"],
[-1, "0B"],
[2048, "2K"],
[1024 * 1024, "1M"],
[5 * 1024 * 1024, "5M"],
[2 * 1024 * 1024 * 1024, "2.0G"],
];
for (const [bytes, expected] of cases) {
it(`${bytes} -> ${expected}`, () => {
expect(formatHeap(bytes)).toBe(expected);
});
}
});
describe("formatTime", () => {
it("formats mm:ss and clamps negatives", () => {
expect(formatTime(0)).toBe("00:00");
expect(formatTime(65_000)).toBe("01:05");
expect(formatTime(-10)).toBe("00:00");
});
});
describe("fractionFor", () => {
it("centers a lone point and spreads the rest across 0..1", () => {
expect(fractionFor(0, 1)).toBe(0.5);
expect(fractionFor(0, 5)).toBe(0);
expect(fractionFor(4, 5)).toBe(1);
expect(fractionFor(2, 5)).toBe(0.5);
});
});
// Bug class: a missing sample must lift the pen (M) so the chart does not draw
// a straight line bridging the gap, which would imply data that was never
// measured.
describe("buildPath gap handling", () => {
it("starts a new subpath after each undefined value", () => {
const samples = [{ v: 0 }, { v: 100 }, { v: undefined }, { v: 50 }];
const path = buildPath(samples, (s) => s.v, 100);
const commands = path.match(/[ML]/g);
expect(commands).toEqual(["M", "L", "M"]);
expect(path.startsWith("M0.0000,1.0000")).toBe(true);
});
it("emits empty string when every sample is missing", () => {
const samples = [{ v: undefined }, { v: undefined }];
expect(buildPath(samples, (s) => s.v, 100)).toBe("");
});
it("clamps values above the ceiling to the top of the lane", () => {
const path = buildPath([{ v: 200 }], (s) => s.v, 100);
expect(path).toBe("M0.5000,0.0000");
});
});
@@ -0,0 +1,42 @@
import { describe, it, expect } from "bun:test";
import {
STATUS_ORDER,
statusFor,
statusForStep,
} from "../lib/property-status";
import { step } from "./fixtures";
// Bug class: RunDetail and ViolationsPanel once carried two copies of this
// status logic; if they drift, the same property shows a different verdict in
// the timeline vs the violations list. Both panels now share statusFor, so its
// precedence and the violated-first ordering must stay pinned.
describe("statusFor", () => {
it("ranks violated over holds and defaults missing residuals to pending", () => {
const violations = new Set(["v"]);
expect(statusFor("v", violations, { v: { op: "true" } })).toBe("violated");
expect(statusFor("h", violations, { h: { op: "true" } })).toBe("holds");
expect(statusFor("p", violations, { p: { op: "false" } })).toBe("pending");
expect(statusFor("x", violations, undefined)).toBe("pending");
});
});
describe("statusForStep", () => {
it("matches statusFor for the same step and is pending for a null step", () => {
const s = step({
violations: ["v"],
residuals: { v: { op: "true" }, h: { op: "true" } },
});
expect(statusForStep("v", s)).toBe("violated");
expect(statusForStep("h", s)).toBe("holds");
expect(statusForStep("v", null)).toBe("pending");
});
});
describe("STATUS_ORDER", () => {
it("sorts violated before pending before holds", () => {
const sorted = ["holds", "violated", "pending"].sort(
(a, b) => STATUS_ORDER[a as never] - STATUS_ORDER[b as never],
);
expect(sorted).toEqual(["violated", "pending", "holds"]);
});
});
@@ -0,0 +1,81 @@
import { describe, it, expect } from "bun:test";
import {
buildRunHistory,
collectPropertyNames,
sortLanes,
statusForProperty,
} from "../lib/run-history";
import type { PropertyLane } from "../panels/Timeline";
import type { Run } from "../types";
import { step, summary } from "./fixtures";
function lane(name: string, statuses: PropertyLane["statuses"]): PropertyLane {
return { name, statuses };
}
describe("collectPropertyNames", () => {
it("dedups and sorts names across steps, skipping null and residual-less steps", () => {
const names = collectPropertyNames([
null,
step({ residuals: { b: { op: "true" }, a: { op: "false" } } }),
step({}),
step({ residuals: { a: { op: "true" }, c: { op: "true" } } }),
]);
expect(names).toEqual(["a", "b", "c"]);
});
});
// Bug class: getting status precedence wrong (e.g. checking residual before
// the violation set, or not defaulting null/absent to pending) would paint a
// violated property lane green.
describe("statusForProperty", () => {
it("ranks violated over a holding residual and defaults to pending", () => {
const s = step({ violations: ["p"], residuals: { p: { op: "true" } } });
expect(statusForProperty("p", s)).toBe("violated");
expect(statusForProperty("q", step({ residuals: { q: { op: "true" } } }))).toBe("holds");
expect(statusForProperty("q", step({ residuals: { q: { op: "false" } } }))).toBe("pending");
expect(statusForProperty("p", null)).toBe("pending");
});
});
// Bug class: a lane that ever violated must sort first; trailing-pending lanes
// rank ahead of fully-holding ones, else the timeline buries active failures.
describe("sortLanes", () => {
it("orders violated, then trailing-pending, then holds, ties by name", () => {
const ordered = sortLanes([
lane("holds-b", ["holds", "holds"]),
lane("pending-a", ["holds", "pending"]),
lane("violated-z", ["holds", "violated", "holds"]),
lane("holds-a", ["holds", "holds"]),
]).map((l) => l.name);
expect(ordered).toEqual(["violated-z", "pending-a", "holds-a", "holds-b"]);
});
});
describe("buildRunHistory", () => {
it("aligns lane statuses, metrics samples, and first-violation index by position", () => {
const run = {
id: "run-1",
steps: [
summary({ index: 0 }),
summary({ index: 1, has_violations: true }),
summary({ index: 2, has_exceptions: true }),
],
} as unknown as Run;
const responses = [
step({ step: 0, residuals: { p: { op: "true" } } }),
step({ step: 1, violations: ["p"], residuals: { p: { op: "true" } } }),
null,
];
const history = buildRunHistory(run, responses);
expect(history.names).toEqual(["p"]);
expect(history.lanes[0].statuses).toEqual(["holds", "violated", "pending"]);
expect(history.firstViolationStep).toBe(1);
expect(history.firstExceptionStep).toBe(2);
expect(history.violationStepIndices).toEqual([1]);
expect(history.exceptionStepIndices).toEqual([2]);
expect(history.metricsSamples.map((m) => m.stepIndex)).toEqual([0, 1, 2]);
});
});
@@ -0,0 +1,67 @@
import { describe, it, expect } from "bun:test";
import {
canonicalize,
flatten,
getAtPath,
stableStringify,
} from "../lib/snapshot-diff";
// Bug class: a path off-by-one in the getAtPath regex parse resolves the wrong
// node, so every diff between two snapshots is mis-reported. flatten emits the
// paths the diff later feeds back through getAtPath, so every emitted path must
// resolve to the same value flatten recorded.
describe("flatten/getAtPath round-trip", () => {
const cases: { name: string; input: Record<string, unknown> }[] = [
{ name: "nested objects", input: { a: { b: { c: 1 } } } },
{
name: "array longer than inline limit indexes each element",
input: { items: [10, 20, 30, 40] },
},
{
name: "objects inside an expanded array",
input: { rows: [{ id: 1 }, { id: 2 }, { id: 3 }] },
},
{
name: "keys with dots are matched verbatim before regex split",
input: { "a.b": 7 },
},
{
name: "mixed nesting",
input: { ui: { tabs: ["x", "y", "z", "w"], open: true }, n: 0 },
},
];
for (const { name, input } of cases) {
it(name, () => {
for (const row of flatten(input)) {
expect(stableStringify(getAtPath(input, row.path))).toBe(
stableStringify(row.value),
);
}
});
}
it("indexes array elements by their real position, not off by one", () => {
const input = { items: ["a", "b", "c", "d"] };
const rows = flatten(input);
expect(getAtPath(input, "items[0]")).toBe("a");
expect(getAtPath(input, "items[3]")).toBe("d");
expect(rows.map((r) => r.path)).toEqual([
"items[0]",
"items[1]",
"items[2]",
"items[3]",
]);
});
});
describe("canonicalize", () => {
it("orders object keys so reordered snapshots compare equal", () => {
expect(stableStringify({ b: 1, a: 2 })).toBe(stableStringify({ a: 2, b: 1 }));
expect(canonicalize({ b: 1, a: 2 })).toEqual({ a: 2, b: 1 });
});
it("preserves array order", () => {
expect(stableStringify([3, 1, 2])).not.toBe(stableStringify([1, 2, 3]));
});
});
+24
View File
@@ -0,0 +1,24 @@
import { describe, it, expect } from "bun:test";
import { clampIndex } from "../hooks/useStep";
// Bug class: a wrong boundary lets the URL address step 0 or a step past the
// end, so the viewer requests a non-existent step and renders nothing. Steps
// are 1-based and capped at maxIndex.
describe("clampIndex", () => {
const cases: [number, number | undefined, number][] = [
[0, 5, 1],
[-3, 5, 1],
[1, 5, 1],
[3, 5, 3],
[5, 5, 5],
[6, 5, 5],
[100, 5, 5],
[3, undefined, 3],
[0, undefined, 1],
];
for (const [index, max, expected] of cases) {
it(`clamps (${index}, ${max}) -> ${expected}`, () => {
expect(clampIndex(index, max)).toBe(expected);
});
}
});