Files
genshin-assistant/electron/devControlServer.ts
T
AzuTear 639b0b7f59 feat(scanner): add native artifact pipeline
Add native IK-style capture processing, Artifact Inventory, explicit promotion and single-result review. Confirm the three live OCR corrections in the eval corpus and preserve extraction/value separation.
2026-07-09 23:30:42 +02:00

507 lines
23 KiB
TypeScript

import fs from "node:fs/promises";
import http, { type Server } from "node:http";
import path from "node:path";
import { execFile } from "node:child_process";
import { promisify } from "node:util";
import type {
CaptureOptions,
CaptureResult,
CaptureSourceInfo,
ClickResult,
ReviewSampleListResult,
NativeScannerCatalogStatus,
NativeScannerDataStatus,
NativeScannerImageLoadStatus,
NativeScannerPreflightStatus,
NativeScannerProcessStatus,
NativeScannerResultsLoadStatus,
NativeScannerRunStatus,
ScannerCommand,
ScannerStatusPayload,
AppRuntimeInfo,
} from "../src/types/global.js";
import { validateLookupPackage } from "../src/lib/genshinLookup.js";
const execFileAsync = promisify(execFile);
interface DevControlServerDependencies {
registeredHotkeys: Record<string, boolean>;
appBuild: AppRuntimeInfo;
hasMainWindow: () => boolean;
sendScannerCommand: (command: ScannerCommand | "probe-click") => void;
clickScreen: (x: number, y: number) => Promise<ClickResult>;
scannerStatus: () => ScannerStatusPayload;
nativeScannerDataStatus: () => Promise<NativeScannerDataStatus>;
nativeScannerCatalog: () => Promise<NativeScannerCatalogStatus>;
nativeScannerPreflight: (options?: { category?: string }) => Promise<NativeScannerPreflightStatus>;
nativeScannerStart: (options?: { limit?: number; category?: string }) => Promise<NativeScannerRunStatus>;
nativeScannerStop: () => Promise<NativeScannerRunStatus>;
nativeScannerStatus: () => Promise<NativeScannerRunStatus>;
nativeScannerProcessRun: (options?: { runDir?: string; persist?: boolean; limit?: number }) => Promise<NativeScannerProcessStatus>;
nativeScannerLoadResults: (options?: { runDir?: string; limit?: number }) => Promise<NativeScannerResultsLoadStatus>;
nativeScannerLoadImage: (options: { runDir?: string; imagePath: string }) => Promise<NativeScannerImageLoadStatus>;
warmOcr: (engine: "current") => Promise<unknown>;
loadReviewSamples: (limit?: number) => Promise<ReviewSampleListResult>;
listCaptureSources: () => Promise<CaptureSourceInfo[]>;
captureSource: (
id: string,
delayMs?: number,
focusGenshin?: boolean,
options?: CaptureOptions,
) => Promise<CaptureResult>;
requestShutdown?: (reason: string) => void;
}
function writeDevJson(res: http.ServerResponse, statusCode: number, payload: unknown) {
res.writeHead(statusCode, {
"content-type": "application/json; charset=utf-8",
"cache-control": "no-store",
});
res.end(JSON.stringify(payload));
}
function dataUrlBase64(dataUrl: string) {
return dataUrl.replace(/^data:image\/png;base64,/, "");
}
function devCaptureOutputDir() {
return path.join(process.cwd(), "outputs", "live-capture");
}
function safeDebugFilePart(value: string) {
return value.replace(/[^A-Za-z0-9._-]+/g, "-").replace(/^-+|-+$/g, "").slice(0, 80) || "capture";
}
function dataUrlFingerprint(dataUrl: string | undefined) {
if (!dataUrl) return "";
let hash = 2166136261;
const stride = Math.max(1, Math.floor(dataUrl.length / 4096));
for (let index = 0; index < dataUrl.length; index += stride) {
hash ^= dataUrl.charCodeAt(index);
hash = Math.imul(hash, 16777619);
}
return `${dataUrl.length.toString(16)}:${(hash >>> 0).toString(16)}`;
}
async function writeDevCaptureImage(filePath: string, dataUrl: string | undefined) {
if (!dataUrl) return null;
await fs.writeFile(filePath, Buffer.from(dataUrlBase64(dataUrl), "base64"));
return filePath;
}
async function writeDevCaptureSnapshot(capture: CaptureResult) {
const outputDir = devCaptureOutputDir();
await fs.mkdir(outputDir, { recursive: true });
const stamp = new Date().toISOString().replace(/[\\/:]/g, "-").replace(/\..+?$/, "");
const prefix = safeDebugFilePart(`${stamp}-${capture.name}`);
const files = {
full: await writeDevCaptureImage(path.join(outputDir, `${prefix}-full.png`), capture.dataUrl),
detail: await writeDevCaptureImage(path.join(outputDir, `${prefix}-detail.png`), capture.detailDataUrl),
inventory: await writeDevCaptureImage(path.join(outputDir, `${prefix}-inventory.png`), capture.inventoryDataUrl),
crops: [] as Array<{ id: string; label: string; path: string; rect: { x: number; y: number; width: number; height: number } }>,
};
for (const crop of capture.crops ?? []) {
const cropPath = path.join(outputDir, `${prefix}-${safeDebugFilePart(crop.id)}.png`);
const written = await writeDevCaptureImage(cropPath, crop.dataUrl);
if (written) files.crops.push({ id: crop.id, label: crop.label, path: written, rect: crop.rect });
}
const summary = {
id: capture.id,
name: capture.name,
width: capture.width,
height: capture.height,
capturedAt: capture.capturedAt,
captureTarget: capture.captureTarget,
ocrSkipped: capture.ocrSkipped,
ocrTimedOut: capture.ocrTimedOut,
layout: capture.layout,
inventoryGrid: capture.inventoryGrid
? {
rows: capture.inventoryGrid.rows,
cols: capture.inventoryGrid.cols,
confidence: capture.inventoryGrid.confidence,
source: capture.inventoryGrid.source,
firstCenter: capture.inventoryGrid.centers[0] ?? null,
lastCenter: capture.inventoryGrid.centers.at(-1) ?? null,
}
: null,
inventoryCount: capture.inventoryCount ?? null,
locked: capture.locked,
lockSignal: capture.lockSignal,
crops: (capture.crops ?? []).map((crop) => ({ id: crop.id, label: crop.label, rect: crop.rect })),
ocr: capture.ocr ?? [],
files,
};
const summaryPath = path.join(outputDir, `${prefix}-summary.json`);
await fs.writeFile(summaryPath, JSON.stringify(summary, null, 2), "utf8");
return { ...summary, summaryPath };
}
function wait(ms: number) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
function findGenshinSource(sources: CaptureSourceInfo[], sourceId: string | null) {
return sourceId
? sources.find((entry) => entry.id === sourceId)
: sources.find((entry) => entry.isGenshinCandidate);
}
function sourceListForError(sources: CaptureSourceInfo[]) {
return sources.map(({ id, name, isGenshinCandidate }) => ({ id, name, isGenshinCandidate }));
}
export function createDevControlServer(deps: DevControlServerDependencies): Server {
const server = http.createServer((req, res) => {
if (req.socket.remoteAddress && !["127.0.0.1", "::1", "::ffff:127.0.0.1"].includes(req.socket.remoteAddress)) {
writeDevJson(res, 403, { ok: false, error: "local only" });
return;
}
const url = new URL(req.url ?? "/", "http://127.0.0.1");
if (url.pathname === "/health") {
writeDevJson(res, 200, { ok: true, hotkeys: deps.registeredHotkeys, hasWindow: deps.hasMainWindow(), appBuild: deps.appBuild });
return;
}
if (url.pathname === "/dev/shutdown") {
if (!deps.requestShutdown) {
writeDevJson(res, 501, { ok: false, error: "shutdown not supported" });
return;
}
const reason = url.searchParams.get("reason") || "dev-control shutdown requested";
writeDevJson(res, 200, { ok: true, appBuild: deps.appBuild, reason });
setTimeout(() => deps.requestShutdown?.(reason), 50);
return;
}
if (url.pathname === "/scanner/start") {
const limit = Number(url.searchParams.get("limit") ?? Number.NaN);
const hasLimit = Number.isFinite(limit) && limit > 0;
const category = url.searchParams.get("category") ?? undefined;
deps.nativeScannerStart({ ...(hasLimit ? { limit } : {}), ...(category ? { category } : {}) })
.then((scanner) => writeDevJson(res, 200, { ok: true, scanner }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/stop") {
deps.nativeScannerStop()
.then((scanner) => writeDevJson(res, 200, { ok: true, scanner }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/probe") {
deps.sendScannerCommand("probe-click");
writeDevJson(res, 200, { ok: true, command: "probe-click" });
return;
}
if (url.pathname === "/automation/click") {
const x = Number(url.searchParams.get("x"));
const y = Number(url.searchParams.get("y"));
if (!Number.isFinite(x) || !Number.isFinite(y)) {
writeDevJson(res, 400, { ok: false, error: "x and y query params are required" });
return;
}
deps.clickScreen(Math.round(x), Math.round(y))
.then((payload: unknown) => writeDevJson(res, 200, { ok: true, payload }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/status") {
deps.nativeScannerStatus()
.then((nativeScanner) => writeDevJson(res, 200, { ok: true, status: deps.scannerStatus(), nativeScanner }))
.catch(() => writeDevJson(res, 200, { ok: true, status: deps.scannerStatus() }));
return;
}
if (url.pathname === "/scanner/native/data") {
deps.nativeScannerDataStatus()
.then((status) => writeDevJson(res, status.valid ? 200 : 409, { ok: status.valid, status }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/native/catalog") {
deps.nativeScannerCatalog()
.then((catalog) => writeDevJson(res, catalog.data.valid ? 200 : 409, { ok: catalog.data.valid, catalog }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/native/preflight") {
const category = url.searchParams.get("category") ?? undefined;
deps.nativeScannerPreflight(category ? { category } : undefined)
.then((status) => writeDevJson(res, status.ready ? 200 : 409, { ok: status.ready, status }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/native/process") {
const runDir = url.searchParams.get("runDir") ?? undefined;
const persist = url.searchParams.get("persist") === "1";
const limit = Number(url.searchParams.get("limit") ?? Number.NaN);
deps.nativeScannerProcessRun({
runDir,
persist,
limit: Number.isFinite(limit) && limit > 0 ? limit : undefined,
})
.then((status) => writeDevJson(res, status.ok ? 200 : 409, { ok: status.ok, status }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/native/results") {
const runDir = url.searchParams.get("runDir") ?? undefined;
const limit = Number(url.searchParams.get("limit") ?? Number.NaN);
deps.nativeScannerLoadResults({
runDir,
limit: Number.isFinite(limit) && limit > 0 ? limit : undefined,
})
.then((status) => writeDevJson(res, status.ok ? 200 : 409, { ok: status.ok, status }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/native/image") {
const runDir = url.searchParams.get("runDir") ?? undefined;
const imagePath = url.searchParams.get("imagePath");
if (!imagePath) {
writeDevJson(res, 400, { ok: false, error: "imagePath query param is required" });
return;
}
deps.nativeScannerLoadImage({ runDir, imagePath })
.then((status) => writeDevJson(res, status.ok ? 200 : 409, { ok: status.ok, status }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/ocr/warmup") {
deps.warmOcr("current")
.then((status) => writeDevJson(res, 200, { ok: true, status }))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/lookup/status") {
const status = validateLookupPackage();
writeDevJson(res, status.valid ? 200 : 409, { ok: status.valid, status });
return;
}
if (url.pathname === "/scanner/lookup/regenerate") {
execFileAsync("node", ["scripts/generate-genshin-data.cjs"], { cwd: process.cwd(), windowsHide: true, timeout: 120000 })
.then(({ stdout, stderr }) => {
const status = validateLookupPackage();
writeDevJson(res, status.valid ? 200 : 409, { ok: status.valid, status, stdout, stderr });
})
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/scanner/benchmark-ocr") {
const limit = Math.max(1, Math.min(100, Number(url.searchParams.get("limit") ?? 1) || 1));
const sourceId = url.searchParams.get("sourceId");
const profileParam = url.searchParams.get("profile");
const ocrProfile: "full" | "fast" = profileParam === "full" ? "full" : "fast";
deps.listCaptureSources()
.then(async (sources) => {
const source = findGenshinSource(sources, sourceId);
if (!source) {
writeDevJson(res, 404, { ok: false, error: "No Genshin capture source found.", sources: sourceListForError(sources) });
return;
}
const benchmarkSource = source;
async function runCurrentBenchmark() {
const startedAt = Date.now();
const captures: Array<{
index: number;
elapsedMs: number;
ocrFields: number;
timedOut: boolean;
ocrSkipped: boolean;
artifactDetailConfidence: number;
sanctified: boolean;
prepareMs: number;
ocrMs: number;
totalMs: number;
ocrProfile?: "full" | "fast";
ocrWorkerPoolSize?: number;
ocrFieldMs?: Record<string, number>;
}> = [];
for (let index = 0; index < limit; index += 1) {
const captureStartedAt = Date.now();
const capture = await deps.captureSource(benchmarkSource.id, index === 0 ? 150 : 0, true, {
ocrMode: "artifact",
ocrProfile,
ocrEngine: "current",
omitFullFrame: true,
omitInventoryPreview: true,
skipOcrUnlessArtifactDetail: true,
});
captures.push({
index,
elapsedMs: Date.now() - captureStartedAt,
ocrFields: capture.ocr?.length ?? 0,
timedOut: Boolean(capture.ocrTimedOut),
ocrSkipped: Boolean(capture.ocrSkipped),
artifactDetailConfidence: capture.artifactDetail?.confidence ?? 0,
sanctified: Boolean(capture.sanctified),
prepareMs: capture.timings?.prepareMs ?? 0,
ocrMs: capture.timings?.ocrMs ?? 0,
totalMs: capture.timings?.totalMs ?? 0,
ocrProfile: capture.timings?.ocrProfile,
ocrWorkerPoolSize: capture.timings?.ocrWorkerPoolSize,
ocrFieldMs: capture.timings?.ocrFieldMs,
});
}
const elapsedMs = Date.now() - startedAt;
const timings = captures.map((capture) => capture.elapsedMs).sort((left, right) => left - right);
const ocrTimings = captures.map((capture) => capture.ocrMs).filter((value) => value > 0).sort((left, right) => left - right);
const averageMs = Math.round(elapsedMs / limit);
const averageOcrMs = ocrTimings.length > 0
? Math.round(ocrTimings.reduce((total, value) => total + value, 0) / ocrTimings.length)
: 0;
const percentile = (ratio: number) => timings[Math.min(timings.length - 1, Math.max(0, Math.ceil(timings.length * ratio) - 1))] ?? 0;
const ocrPercentile = (ratio: number) => ocrTimings[Math.min(ocrTimings.length - 1, Math.max(0, Math.ceil(ocrTimings.length * ratio) - 1))] ?? 0;
const ocrFieldTotals = captures.reduce<Record<string, { totalMs: number; count: number; maxMs: number }>>((fields, capture) => {
for (const [field, elapsed] of Object.entries(capture.ocrFieldMs ?? {})) {
const current = fields[field] ?? { totalMs: 0, count: 0, maxMs: 0 };
current.totalMs += elapsed;
current.count += 1;
current.maxMs = Math.max(current.maxMs, elapsed);
fields[field] = current;
}
return fields;
}, {});
const ocrFieldAverages = Object.fromEntries(
Object.entries(ocrFieldTotals).map(([field, timing]) => [
field,
{
averageMs: Math.round(timing.totalMs / Math.max(1, timing.count)),
maxMs: timing.maxMs,
count: timing.count,
},
]),
);
return {
engine: "current",
nativeTesseract: "not-enabled",
workerPoolSize: captures.find((capture) => capture.ocrWorkerPoolSize)?.ocrWorkerPoolSize ?? null,
ocrProfile,
limit,
elapsedMs,
averageMs,
averageOcrMs,
minMs: timings[0] ?? 0,
p50Ms: percentile(0.5),
p90Ms: percentile(0.9),
maxMs: timings[timings.length - 1] ?? 0,
ocrP50Ms: ocrPercentile(0.5),
ocrP90Ms: ocrPercentile(0.9),
ocrFieldAverages,
projectedMs: {
artifacts20: averageMs * 20,
artifacts45: averageMs * 45,
artifacts100: averageMs * 100,
},
skippedOcrCaptures: captures.filter((capture) => capture.ocrSkipped).length,
captures,
};
}
const summary = await runCurrentBenchmark();
writeDevJson(res, 200, {
ok: true,
summary,
});
})
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/review/samples") {
deps.loadReviewSamples(Number(url.searchParams.get("limit") ?? 20))
.then((payload: unknown) => writeDevJson(res, 200, payload))
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/capture/smart") {
const sourceId = url.searchParams.get("sourceId");
const focus = url.searchParams.get("focus") !== "0";
const skipOcr = url.searchParams.get("skipOcr") === "1";
deps.listCaptureSources()
.then(async (sources) => {
const source = findGenshinSource(sources, sourceId);
if (!source) {
writeDevJson(res, 404, { ok: false, error: "No Genshin capture source found.", sources: sourceListForError(sources) });
return;
}
const capture = await deps.captureSource(source.id, 250, focus, { skipOcr });
const summary = await writeDevCaptureSnapshot(capture);
writeDevJson(res, 200, { ok: true, source: { id: source.id, name: source.name }, summary });
})
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
if (url.pathname === "/automation/probe-click") {
const sourceId = url.searchParams.get("sourceId");
const requestedIndex = Number(url.searchParams.get("index") ?? "1");
const requestedRow = Number(url.searchParams.get("row") ?? Number.NaN);
const requestedCol = Number(url.searchParams.get("col") ?? Number.NaN);
deps.listCaptureSources()
.then(async (sources) => {
const source = findGenshinSource(sources, sourceId);
if (!source) {
writeDevJson(res, 404, { ok: false, error: "No Genshin capture source found.", sources: sourceListForError(sources) });
return;
}
const before = await deps.captureSource(source.id, 150, true, { skipOcr: true });
const grid = before.inventoryGrid;
const detail = before.artifactDetail;
const gridReady = before.captureTarget === "genshin-client"
&& grid?.source === "detected"
&& (grid.confidence ?? 0) >= 60;
const detailReady = Boolean(detail?.present && detail.confidence >= 45);
if (!gridReady || !detailReady) {
writeDevJson(res, 409, {
ok: false,
error: "Artifact inventory detail view is not ready for probe-click.",
captureTarget: before.captureTarget,
grid: grid ? { rows: grid.rows, cols: grid.cols, source: grid.source, confidence: grid.confidence } : null,
artifactDetail: detail ?? null,
});
return;
}
const centers = before.inventoryGrid?.centers ?? [];
const target = Number.isFinite(requestedRow) && Number.isFinite(requestedCol)
? centers.find((center) => center.row === requestedRow && center.col === requestedCol)
: centers[Math.max(0, Math.min(centers.length - 1, Number.isFinite(requestedIndex) ? requestedIndex : 1))];
if (!target) {
writeDevJson(res, 409, { ok: false, error: "No inventory grid target available.", grid: before.inventoryGrid ?? null });
return;
}
const beforeFingerprint = dataUrlFingerprint(before.detailDataUrl);
const click = await deps.clickScreen(target.x, target.y);
await wait(650);
const after = await deps.captureSource(source.id, 0, true, { skipOcr: true });
const afterFingerprint = dataUrlFingerprint(after.detailDataUrl);
const changed = Boolean(beforeFingerprint && afterFingerprint && beforeFingerprint !== afterFingerprint);
writeDevJson(res, 200, {
ok: Boolean(click.ok && click.clicked && changed),
changed,
target,
click,
before: {
captureTarget: before.captureTarget,
grid: before.inventoryGrid ? { rows: before.inventoryGrid.rows, cols: before.inventoryGrid.cols, source: before.inventoryGrid.source, confidence: before.inventoryGrid.confidence } : null,
detailFingerprint: beforeFingerprint,
},
after: {
captureTarget: after.captureTarget,
grid: after.inventoryGrid ? { rows: after.inventoryGrid.rows, cols: after.inventoryGrid.cols, source: after.inventoryGrid.source, confidence: after.inventoryGrid.confidence } : null,
detailFingerprint: afterFingerprint,
},
});
})
.catch((error: unknown) => writeDevJson(res, 500, { ok: false, error: error instanceof Error ? error.message : String(error) }));
return;
}
writeDevJson(res, 404, { ok: false, error: "unknown endpoint" });
});
server.listen(17317, "127.0.0.1");
return server;
}