oh-my-opencode 4.9.2 → 4.11.0

package/dist/skills/visual-qa/scripts/png-decode.ts

@@ -0,0 +1,206 @@
+import { Buffer } from "node:buffer"
+import { inflateSync } from "node:zlib"
+
+import { PNG_SIGNATURE } from "./png-crc"
+import type { DecodedImage } from "./types"
+
+export class PngDecodeError extends Error {
+	readonly name = "PngDecodeError"
+}
+
+interface PngHeader {
+	readonly width: number
+	readonly height: number
+	readonly bitDepth: number
+	readonly colorType: number
+	readonly channels: number
+}
+
+interface PngChunk {
+	readonly type: string
+	readonly data: Buffer
+}
+
+function readChunks(buffer: Buffer): readonly PngChunk[] {
+	const chunks: PngChunk[] = []
+	let offset = 8
+	while (offset + 8 <= buffer.length) {
+		const length = buffer.readUInt32BE(offset)
+		const type = buffer.toString("ascii", offset + 4, offset + 8)
+		const dataStart = offset + 8
+		const dataEnd = dataStart + length
+		if (dataEnd + 4 > buffer.length) break
+		chunks.push({ type, data: buffer.subarray(dataStart, dataEnd) })
+		offset = dataEnd + 4
+	}
+	return chunks
+}
+
+function channelsForColorType(colorType: number): number {
+	switch (colorType) {
+		case 0:
+			return 1
+		case 2:
+			return 3
+		case 4:
+			return 2
+		case 6:
+			return 4
+		default:
+			throw new PngDecodeError(`unsupported color type ${colorType}`)
+	}
+}
+
+function parseHeader(data: Buffer): PngHeader {
+	if (data.length < 13) {
+		throw new PngDecodeError("invalid IHDR chunk length")
+	}
+	const colorType = data[9] ?? 0
+	return {
+		width: data.readUInt32BE(0),
+		height: data.readUInt32BE(4),
+		bitDepth: data[8] ?? 0,
+		colorType,
+		channels: channelsForColorType(colorType),
+	}
+}
+
+function paeth(a: number, b: number, c: number): number {
+	const p = a + b - c
+	const pa = Math.abs(p - a)
+	const pb = Math.abs(p - b)
+	const pc = Math.abs(p - c)
+	if (pa <= pb && pa <= pc) return a
+	if (pb <= pc) return b
+	return c
+}
+
+function unfilterRow(filterType: number, row: Buffer, prev: Buffer | null, bpp: number): Buffer {
+	const out = Buffer.alloc(row.length)
+	for (let i = 0; i < row.length; i++) {
+		const raw = row[i] ?? 0
+		const a = i >= bpp ? (out[i - bpp] ?? 0) : 0
+		const b = prev ? (prev[i] ?? 0) : 0
+		const c = i >= bpp && prev ? (prev[i - bpp] ?? 0) : 0
+		switch (filterType) {
+			case 0:
+				out[i] = raw
+				break
+			case 1:
+				out[i] = (raw + a) & 0xff
+				break
+			case 2:
+				out[i] = (raw + b) & 0xff
+				break
+			case 3:
+				out[i] = (raw + ((a + b) >> 1)) & 0xff
+				break
+			case 4:
+				out[i] = (raw + paeth(a, b, c)) & 0xff
+				break
+			default:
+				throw new PngDecodeError(`unsupported filter type ${filterType}`)
+		}
+	}
+	return out
+}
+
+function decodePixels(idat: Buffer, width: number, height: number, bpp: number): Buffer {
+	const inflated = inflateSync(idat)
+	const rowBytes = width * bpp
+	if (inflated.length < height * (rowBytes + 1)) {
+		throw new PngDecodeError("truncated image data")
+	}
+	const pixels = Buffer.alloc(width * height * bpp)
+	let prev: Buffer | null = null
+	for (let y = 0; y < height; y++) {
+		const rowStart = y * (rowBytes + 1)
+		const filterType = inflated[rowStart] ?? 0
+		const filtered = inflated.subarray(rowStart + 1, rowStart + 1 + rowBytes)
+		const row = unfilterRow(filterType, filtered, prev, bpp)
+		row.copy(pixels, y * rowBytes)
+		prev = row
+	}
+	return pixels
+}
+
+function normalizeToRgba(
+	pixels: Buffer,
+	pixelCount: number,
+	channels: number,
+): { readonly rgba: Uint8Array; readonly hasTransparent: boolean } {
+	const rgba = new Uint8Array(pixelCount * 4)
+	let hasTransparent = false
+	for (let i = 0; i < pixelCount; i++) {
+		const src = i * channels
+		let r = 0
+		let g = 0
+		let b = 0
+		let a = 255
+		switch (channels) {
+			case 1: {
+				const v = pixels[src] ?? 0
+				r = v
+				g = v
+				b = v
+				break
+			}
+			case 2: {
+				const v = pixels[src] ?? 0
+				r = v
+				g = v
+				b = v
+				a = pixels[src + 1] ?? 255
+				break
+			}
+			case 3: {
+				r = pixels[src] ?? 0
+				g = pixels[src + 1] ?? 0
+				b = pixels[src + 2] ?? 0
+				break
+			}
+			default: {
+				r = pixels[src] ?? 0
+				g = pixels[src + 1] ?? 0
+				b = pixels[src + 2] ?? 0
+				a = pixels[src + 3] ?? 255
+			}
+		}
+		const dst = i * 4
+		rgba[dst] = r
+		rgba[dst + 1] = g
+		rgba[dst + 2] = b
+		rgba[dst + 3] = a
+		if (a < 255) hasTransparent = true
+	}
+	return { rgba, hasTransparent }
+}
+
+export function decodePng(buffer: Buffer): DecodedImage {
+	if (buffer.length < 8 || !buffer.subarray(0, 8).equals(PNG_SIGNATURE)) {
+		throw new PngDecodeError("not a PNG file (bad signature)")
+	}
+	const chunks = readChunks(buffer)
+	const ihdr = chunks.find((chunk) => chunk.type === "IHDR")
+	if (ihdr === undefined) {
+		throw new PngDecodeError("missing IHDR chunk")
+	}
+	const header = parseHeader(ihdr.data)
+	if (header.bitDepth !== 8) {
+		throw new PngDecodeError(`unsupported bit depth ${header.bitDepth}`)
+	}
+	const idatChunks = chunks.filter((chunk) => chunk.type === "IDAT")
+	if (idatChunks.length === 0) {
+		throw new PngDecodeError("missing IDAT chunk")
+	}
+	const idat = Buffer.concat(idatChunks.map((chunk) => chunk.data))
+	const pixels = decodePixels(idat, header.width, header.height, header.channels)
+	const normalized = normalizeToRgba(pixels, header.width * header.height, header.channels)
+	return {
+		width: header.width,
+		height: header.height,
+		rgba: normalized.rgba,
+		hasAlphaChannel: header.colorType === 4 || header.colorType === 6,
+		hasTransparentPixels: normalized.hasTransparent,
+	}
+}

package/dist/skills/visual-qa/scripts/png-synth.ts

@@ -0,0 +1,57 @@
+import { Buffer } from "node:buffer"
+import { deflateSync } from "node:zlib"
+
+import { crc32, PNG_SIGNATURE } from "./png-crc"
+
+const BIT_DEPTH_8 = 8
+const COLOR_TYPE_RGBA = 6
+const FILTER_NONE = 0
+const RGBA_CHANNELS = 4
+
+function pngChunk(type: string, data: Buffer): Buffer {
+	const typeBuffer = Buffer.from(type, "ascii")
+	const length = Buffer.alloc(4)
+	length.writeUInt32BE(data.length, 0)
+	const crcBuffer = Buffer.alloc(4)
+	crcBuffer.writeUInt32BE(crc32(Buffer.concat([typeBuffer, data])), 0)
+	return Buffer.concat([length, typeBuffer, data, crcBuffer])
+}
+
+export function encodeRgbaPng(width: number, height: number, rgba: Uint8Array): Buffer {
+	const rowBytes = width * RGBA_CHANNELS
+	const raw = Buffer.alloc(height * (rowBytes + 1))
+	for (let y = 0; y < height; y++) {
+		const rowStart = y * (rowBytes + 1)
+		raw[rowStart] = FILTER_NONE
+		for (let x = 0; x < rowBytes; x++) {
+			raw[rowStart + 1 + x] = rgba[y * rowBytes + x] ?? 0
+		}
+	}
+	const header = Buffer.alloc(13)
+	header.writeUInt32BE(width, 0)
+	header.writeUInt32BE(height, 4)
+	header[8] = BIT_DEPTH_8
+	header[9] = COLOR_TYPE_RGBA
+	return Buffer.concat([
+		PNG_SIGNATURE,
+		pngChunk("IHDR", header),
+		pngChunk("IDAT", deflateSync(raw)),
+		pngChunk("IEND", Buffer.alloc(0)),
+	])
+}
+
+export function solidRgba(
+	width: number,
+	height: number,
+	color: readonly [number, number, number, number],
+): Uint8Array {
+	const rgba = new Uint8Array(width * height * RGBA_CHANNELS)
+	for (let pixel = 0; pixel < width * height; pixel++) {
+		const offset = pixel * RGBA_CHANNELS
+		rgba[offset] = color[0]
+		rgba[offset + 1] = color[1]
+		rgba[offset + 2] = color[2]
+		rgba[offset + 3] = color[3]
+	}
+	return rgba
+}

package/dist/skills/visual-qa/scripts/skill-prompt-contract.test.ts

@@ -0,0 +1,127 @@
+import { describe, expect, test } from "bun:test"
+import { existsSync, readFileSync } from "node:fs"
+import { dirname, join } from "node:path"
+
+const repoRoot = findRepoRoot(import.meta.dir)
+const sharedSkillPath = join(repoRoot, "packages", "shared-skills", "skills", "visual-qa", "SKILL.md")
+const codexSkillPath = join(repoRoot, "packages", "omo-codex", "plugin", "skills", "visual-qa", "SKILL.md")
+const referencesPath = join(
+	repoRoot,
+	"packages",
+	"shared-skills",
+	"skills",
+	"visual-qa",
+	"references",
+	"agent-browser-setup.md",
+)
+
+type PromptFixture = {
+	readonly label: string
+	readonly text: string
+}
+
+function readPrompt(path: string): string {
+	return readFileSync(path, "utf8")
+}
+
+function findRepoRoot(start: string): string {
+	let current = start
+	while (true) {
+		if (existsSync(join(current, "package.json")) && existsSync(join(current, "packages"))) {
+			return current
+		}
+		const parent = dirname(current)
+		if (parent === current) {
+			throw new Error(`repository root not found from ${start}`)
+		}
+		current = parent
+	}
+}
+
+function fixtures(): readonly PromptFixture[] {
+	const promptFixtures: PromptFixture[] = [{ label: "shared skill", text: readPrompt(sharedSkillPath) }]
+	if (existsSync(codexSkillPath)) {
+		promptFixtures.push({ label: "codex plugin copy", text: readPrompt(codexSkillPath) })
+	}
+	return promptFixtures
+}
+
+function sectionBetween(text: string, startMarker: string, endMarker: string): string {
+	const start = text.indexOf(startMarker)
+	if (start < 0) {
+		throw new Error(`missing start marker: ${startMarker}`)
+	}
+	const end = text.indexOf(endMarker, start + startMarker.length)
+	if (end < 0) {
+		throw new Error(`missing end marker: ${endMarker}`)
+	}
+	return text.slice(start, end)
+}
+
+describe("visual-qa skill prompt contract", () => {
+	test("#given visual QA prompts #when dispatching pass B #then the oracle must directly inspect screenshots and content for CJK wrapping", () => {
+		for (const fixture of fixtures()) {
+			const passB = sectionBetween(fixture.text, "### Pass B", "## Step 4")
+			const lowerPassB = passB.toLowerCase()
+
+			expect(lowerPassB, fixture.label).toContain("directly open")
+			expect(lowerPassB, fixture.label).toContain("view_image")
+			expect(lowerPassB, fixture.label).toContain("source code")
+			expect(passB, fixture.label).toContain("[Image #1]")
+			expect(passB, fixture.label).toContain("에이전트 오케스트")
+			expect(passB, fixture.label).toContain("레이션 현황 및 미")
+			expect(passB, fixture.label).toContain("래")
+			expect(passB, fixture.label).toContain("REVISE/FAIL")
+		}
+	})
+
+	test("#given visual QA prompts #when dispatching pass A #then the oracle must reject mock-only UI instead of accepting superficial screenshots", () => {
+		for (const fixture of fixtures()) {
+			const passA = sectionBetween(fixture.text, "### Pass A", "### Pass B")
+			const checkBlock = sectionBetween(passA, "CHECK EACH:", "OUTPUT:")
+			const outputBlock = sectionBetween(passA, "OUTPUT:", '"""')
+			const lowerCheckBlock = checkBlock.toLowerCase()
+
+			expect(lowerCheckBlock, fixture.label).toContain("mock-only")
+			expect(lowerCheckBlock, fixture.label).toContain("faked-with-an-image")
+			expect(lowerCheckBlock, fixture.label).toContain("coherent design tokens")
+			expect(lowerCheckBlock, fixture.label).toContain("reused primitives")
+			expect(lowerCheckBlock, fixture.label).toContain("blocking")
+			expect(outputBlock, fixture.label).toContain("BLOCKING:")
+		}
+	})
+
+	test("#given the Web capture path #when no browser tooling is configured #then it falls back to agent-browser", () => {
+		for (const fixture of fixtures()) {
+			const web = sectionBetween(fixture.text, "### Web", "### TUI")
+
+			expect(web, fixture.label).toContain("agent-browser")
+			expect(fixture.text, fixture.label).toContain("bun add -g agent-browser")
+			expect(fixture.text, fixture.label).toContain("https://github.com/vercel-labs/agent-browser")
+			expect(fixture.text, fixture.label).toContain("references/agent-browser-setup.md")
+		}
+	})
+
+	test("#given the agent-browser fallback #when documenting setup #then a references doc lists install, link, and help", () => {
+		expect(existsSync(referencesPath)).toBe(true)
+		const doc = readFileSync(referencesPath, "utf8")
+
+		expect(doc).toContain("bun add -g agent-browser")
+		expect(doc).toContain("agent-browser install")
+		expect(doc).toContain("https://github.com/vercel-labs/agent-browser")
+		expect(doc).toContain("agent-browser --help")
+	})
+
+	test("#given a clone/design-port task #when in clone-coding mode #then dual pixel + code-fidelity verification loops until both pass", () => {
+		for (const fixture of fixtures()) {
+			const cloneMode = sectionBetween(fixture.text, "## Step 5", "## Reference evidence is not the verdict")
+			const lowerCloneMode = cloneMode.toLowerCase()
+
+			expect(lowerCloneMode, fixture.label).toContain("clone")
+			expect(cloneMode, fixture.label).toContain("pixel-by-pixel")
+			expect(cloneMode, fixture.label).toContain("image-diff")
+			expect(cloneMode, fixture.label).toContain("lazycodex-clone-fidelity-reviewer")
+			expect(lowerCloneMode, fixture.label).toContain("retry")
+		}
+	})
+})

package/dist/skills/visual-qa/scripts/tui-grid.test.ts

@@ -0,0 +1,57 @@
+import { describe, expect, test } from "bun:test"
+
+import { checkTui } from "./tui-grid"
+
+const ESC = String.fromCharCode(0x1b)
+
+describe("checkTui", () => {
+	test("#given ASCII lines within the width #when checked #then there is no overflow", () => {
+		// given / when
+		const result = checkTui("hello\nworld", 80)
+		// then
+		expect(result.lineCount).toBe(2)
+		expect(result.lineWidths).toEqual([5, 5])
+		expect(result.maxWidth).toBe(5)
+		expect(result.overflowLines.length).toBe(0)
+		expect(result.hasAnsi).toBe(false)
+	})
+
+	test("#given a line wider than the expected columns #when checked #then it is flagged as overflow", () => {
+		// given / when
+		const result = checkTui("short\nthis line is definitely too long", 10)
+		// then
+		expect(result.overflowLines.length).toBe(1)
+		expect(result.overflowLines[0]?.line).toBe(2)
+		expect(result.maxWidth).toBeGreaterThan(10)
+	})
+
+	test("#given CJK text #when checked #then wide characters count as two columns", () => {
+		// given / when
+		const result = checkTui("가나다", 80)
+		// then
+		expect(result.lineWidths).toEqual([6])
+		expect(result.wideCharColumns).toEqual([0, 2, 4])
+	})
+
+	test("#given a box whose CJK content is wider than its border #when checked #then borders are misaligned", () => {
+		// given / when
+		const result = checkTui("┌──┐\n│가가│\n└──┘", 80)
+		// then
+		expect(result.borderMisaligned).toBe(true)
+	})
+
+	test("#given a well-formed box #when checked #then borders are aligned", () => {
+		// given / when
+		const result = checkTui("┌──┐\n│ab│\n└──┘", 80)
+		// then
+		expect(result.borderMisaligned).toBe(false)
+	})
+
+	test("#given text with ANSI color codes #when checked #then ANSI is detected and ignored for width", () => {
+		// given / when
+		const result = checkTui(`${ESC}[31mred${ESC}[0m`, 80)
+		// then
+		expect(result.hasAnsi).toBe(true)
+		expect(result.lineWidths).toEqual([3])
+	})
+})

package/dist/skills/visual-qa/scripts/tui-grid.ts

@@ -0,0 +1,88 @@
+import { hasAnsi, stripAnsi } from "./ansi"
+import { charWidth, stringWidth } from "./east-asian-width"
+import type { OverflowLine, TuiCheckResult } from "./types"
+
+const BOX_DRAWING_START = 0x2500
+const BOX_DRAWING_END = 0x257f
+const MAX_WIDE_COLUMNS = 64
+
+function splitLines(text: string): string[] {
+	const lines = text.split(/\r?\n/)
+	if (lines.length > 1 && lines[lines.length - 1] === "") lines.pop()
+	return lines
+}
+
+function isFrameLine(plain: string): boolean {
+	for (const char of plain) {
+		const codePoint = char.codePointAt(0)
+		if (codePoint !== undefined && codePoint >= BOX_DRAWING_START && codePoint <= BOX_DRAWING_END) {
+			return true
+		}
+	}
+	return false
+}
+
+function wideStartColumns(plain: string): number[] {
+	const columns: number[] = []
+	let column = 0
+	for (const char of plain) {
+		const codePoint = char.codePointAt(0)
+		if (codePoint === undefined) continue
+		const width = charWidth(codePoint)
+		if (width === 2) columns.push(column)
+		column += width
+	}
+	return columns
+}
+
+function summarize(
+	lineCount: number,
+	maxWidth: number,
+	expectedColumns: number,
+	overflowCount: number,
+	borderMisaligned: boolean,
+	containsAnsi: boolean,
+): string {
+	const parts = [`${lineCount} line(s)`, `max width ${maxWidth}/${expectedColumns}`]
+	if (overflowCount > 0) parts.push(`${overflowCount} overflow line(s)`)
+	if (borderMisaligned) parts.push("borders misaligned")
+	if (containsAnsi) parts.push("contains ANSI")
+	return `${parts.join("; ")}.`
+}
+
+export function checkTui(text: string, expectedColumns: number): TuiCheckResult {
+	const lines = splitLines(text)
+	const lineWidths: number[] = []
+	const overflowLines: OverflowLine[] = []
+	const wideColumns = new Set<number>()
+	const frameWidths = new Set<number>()
+
+	for (let index = 0; index < lines.length; index++) {
+		const plain = stripAnsi(lines[index] ?? "")
+		const width = stringWidth(plain)
+		lineWidths.push(width)
+		if (expectedColumns > 0 && width > expectedColumns) {
+			overflowLines.push({ line: index + 1, width })
+		}
+		if (isFrameLine(plain)) frameWidths.add(width)
+		for (const column of wideStartColumns(plain)) {
+			if (wideColumns.size < MAX_WIDE_COLUMNS) wideColumns.add(column)
+		}
+	}
+
+	const maxWidth = lineWidths.reduce((max, width) => (width > max ? width : max), 0)
+	const borderMisaligned = frameWidths.size > 1
+	const containsAnsi = hasAnsi(text)
+	return {
+		command: "tui-check",
+		expectedColumns,
+		lineCount: lines.length,
+		lineWidths,
+		maxWidth,
+		overflowLines,
+		borderMisaligned,
+		wideCharColumns: [...wideColumns].sort((a, b) => a - b),
+		hasAnsi: containsAnsi,
+		summary: summarize(lines.length, maxWidth, expectedColumns, overflowLines.length, borderMisaligned, containsAnsi),
+	}
+}

package/dist/skills/visual-qa/scripts/types.ts

@@ -0,0 +1,54 @@
+export interface DecodedImage {
+	readonly width: number
+	readonly height: number
+	readonly rgba: Uint8Array
+	readonly hasAlphaChannel: boolean
+	readonly hasTransparentPixels: boolean
+}
+
+export interface Hotspot {
+	readonly gridX: number
+	readonly gridY: number
+	readonly x: number
+	readonly y: number
+	readonly width: number
+	readonly height: number
+	readonly diffRatio: number
+}
+
+export interface ImageDimensions {
+	readonly width: number
+	readonly height: number
+}
+
+export interface ImageDiffResult {
+	readonly command: "image-diff"
+	readonly dimensionsMatch: boolean
+	readonly reference: ImageDimensions
+	readonly actual: ImageDimensions
+	readonly totalPixels: number
+	readonly diffPixels: number
+	readonly diffRatio: number
+	readonly similarityScore: number
+	readonly alphaChannelIntact: boolean
+	readonly hotspots: readonly Hotspot[]
+	readonly summary: string
+}
+
+export interface OverflowLine {
+	readonly line: number
+	readonly width: number
+}
+
+export interface TuiCheckResult {
+	readonly command: "tui-check"
+	readonly expectedColumns: number
+	readonly lineCount: number
+	readonly lineWidths: readonly number[]
+	readonly maxWidth: number
+	readonly overflowLines: readonly OverflowLine[]
+	readonly borderMisaligned: boolean
+	readonly wideCharColumns: readonly number[]
+	readonly hasAnsi: boolean
+	readonly summary: string
+}

package/dist/tools/background-task/clients.d.ts

@@ -19,6 +19,8 @@ export type BackgroundOutputMessage = {
         }>;
         output?: string;
         name?: string;
+        tool?: string;
+        input?: unknown;
     }>;
 };
 export type BackgroundOutputMessagesResult = {

package/dist/tools/background-task/full-session-format.d.ts

@@ -6,4 +6,5 @@ export declare function formatFullSession(task: BackgroundTask, client: Backgrou
     sinceMessageId?: string;
     includeToolResults: boolean;
     thinkingMaxChars?: number;
+    fromEnd?: boolean;
 }): Promise<string>;

package/dist/tools/background-task/types.d.ts

@@ -12,6 +12,7 @@ export interface BackgroundOutputArgs {
     message_limit?: number;
     since_message_id?: string;
     include_tool_results?: boolean;
+    from_end?: boolean;
     thinking_max_chars?: number;
 }
 export interface BackgroundCancelArgs {

package/dist/tools/delegate-task/background-task-description.d.ts

@@ -0,0 +1,2 @@
+import type { DelegateTaskArgs } from "./types";
+export declare function getPersistedBackgroundTaskDescription(args: DelegateTaskArgs, agent: string): string;