feat(baoyu-image-gen): add codex-cli provider wrapping codex-imagegen

Expose Codex CLI's built-in image_gen tool through baoyu-image-gen's
standard CLI + batch flow as a dedicated provider. The provider spawns
the bundled scripts/codex-imagegen/main.ts (synced from
packages/baoyu-codex-imagegen/src/) so the skill remains self-contained
and inherits retry, cache, file-lock, and JSONL logging. No
OPENAI_API_KEY required — uses the user's Codex subscription.

New env vars: BAOYU_CODEX_IMAGEGEN_{BIN,CACHE_DIR,TIMEOUT_MS,RETRIES,LOG_FILE}.
Hyphenated provider names now resolve under-scored env vars (e.g.,
BAOYU_IMAGE_GEN_CODEX_CLI_CONCURRENCY). codex-cli is never auto-selected
— pin via --provider or default_provider in EXTEND.md.
This commit is contained in:
Jim Liu 宝玉
2026-05-25 00:18:27 -05:00
parent 23fac03691
commit 49e9c46ca4
17 changed files with 1127 additions and 21 deletions
@@ -0,0 +1,80 @@
import { createHash } from "node:crypto";
import { mkdir, readFile, writeFile, copyFile, stat } from "node:fs/promises";
import { existsSync, openSync, closeSync } from "node:fs";
import path from "node:path";
import { setTimeout as delay } from "node:timers/promises";
export function cacheKey(prompt: string, aspect: string, refs: string[]): string {
const h = createHash("sha256");
h.update(prompt);
h.update("|");
h.update(aspect);
h.update("|");
for (const r of [...refs].sort()) h.update(r);
return h.digest("hex").slice(0, 16);
}
export async function lookupCache(cacheDir: string, key: string): Promise<string | null> {
const entry = path.join(cacheDir, `${key}.png`);
try {
const s = await stat(entry);
if (s.size > 1000) return entry;
} catch {}
return null;
}
export async function storeCache(cacheDir: string, key: string, sourcePath: string): Promise<void> {
await mkdir(cacheDir, { recursive: true });
const entry = path.join(cacheDir, `${key}.png`);
await copyFile(sourcePath, entry);
}
export class FileLock {
private fd: number | null = null;
constructor(private lockPath: string) {}
async acquire(timeoutMs = 30_000): Promise<void> {
const start = Date.now();
await mkdir(path.dirname(this.lockPath), { recursive: true });
while (Date.now() - start < timeoutMs) {
try {
this.fd = openSync(this.lockPath, "wx");
return;
} catch (e: any) {
if (e.code !== "EEXIST") throw e;
if (await this.isStale()) {
try {
await this.release(true);
} catch {}
continue;
}
await delay(200);
}
}
throw new Error(`Failed to acquire lock at ${this.lockPath} within ${timeoutMs}ms`);
}
private async isStale(): Promise<boolean> {
try {
const s = await stat(this.lockPath);
return Date.now() - s.mtimeMs > 10 * 60 * 1000;
} catch {
return true;
}
}
async release(force = false): Promise<void> {
if (this.fd != null) {
try {
closeSync(this.fd);
} catch {}
this.fd = null;
}
if (existsSync(this.lockPath) || force) {
const { unlink } = await import("node:fs/promises");
try {
await unlink(this.lockPath);
} catch {}
}
}
}
@@ -0,0 +1,39 @@
import { appendFile, mkdir } from "node:fs/promises";
import path from "node:path";
export interface LogEntry {
ts: string;
level: "info" | "warn" | "error";
event: string;
[k: string]: unknown;
}
export class JsonLogger {
constructor(private logFile: string | null, public verbose: boolean) {}
async log(level: LogEntry["level"], event: string, extra: Record<string, unknown> = {}): Promise<void> {
const entry: LogEntry = { ts: new Date().toISOString(), level, event, ...extra };
const line = JSON.stringify(entry);
if (this.verbose) process.stderr.write(`[${level}] ${event} ${jsonExtras(extra)}\n`);
if (this.logFile) {
await mkdir(path.dirname(this.logFile), { recursive: true });
await appendFile(this.logFile, line + "\n", "utf-8");
}
}
info(event: string, extra?: Record<string, unknown>) {
return this.log("info", event, extra);
}
warn(event: string, extra?: Record<string, unknown>) {
return this.log("warn", event, extra);
}
error(event: string, extra?: Record<string, unknown>) {
return this.log("error", event, extra);
}
}
function jsonExtras(extra: Record<string, unknown>): string {
const entries = Object.entries(extra);
if (entries.length === 0) return "";
return entries.map(([k, v]) => `${k}=${typeof v === "string" ? v : JSON.stringify(v)}`).join(" ");
}
+326
View File
@@ -0,0 +1,326 @@
#!/usr/bin/env bun
import { readFile, mkdir, copyFile, stat } from "node:fs/promises";
import { homedir } from "node:os";
import path from "node:path";
import process from "node:process";
import { setTimeout as delay } from "node:timers/promises";
import { GenError, type CliOptions, type GenerateResult } from "./types.ts";
import { runCodexExec } from "./spawn.ts";
import { findCpToTarget, verifyImageGenWasInvoked, verifyOutput } from "./validator.ts";
import { cacheKey, lookupCache, storeCache, FileLock } from "./cache.ts";
import { JsonLogger } from "./logger.ts";
const HELP = `codex-imagegen — generate images via Codex CLI's image_gen tool
Usage:
codex-imagegen --image <output.png> [--prompt <text> | --prompt-file <path>] [options]
Required:
--image <path> Output PNG path
--prompt <text> Prompt text (or use --prompt-file)
--prompt-file <path> Read prompt from file
Options:
--aspect <ratio> Aspect ratio (1:1, 16:9, 9:16, 4:3, 2.35:1). Default: 1:1
--ref <file> Reference image (repeatable)
--timeout <ms> Codex exec timeout in ms. Default: 300000
--retries <n> Retry attempts on retryable errors. Default: 2
--retry-delay <ms> Base retry delay (exponential). Default: 1500
--cache-dir <path> Enable idempotency cache. Disabled by default.
--log-file <path> Append JSONL log
-v, --verbose Verbose stderr logging
-h, --help Show this help
Stdout: single JSON line on success or failure.
`;
const SHELL_METACHAR = /[;|&`$<>\n\r()'"]/;
function assertSafePath(label: string, value: string): void {
if (SHELL_METACHAR.test(value)) {
throw new GenError(
"invalid_args",
`${label} contains shell metacharacters and would be unsafe to interpolate into the codex instruction: ${value}`,
false,
);
}
}
function parseArgs(argv: string[]): CliOptions {
const opts: CliOptions = {
prompt: "",
promptFile: null,
outputPath: "",
aspect: "1:1",
refImages: [],
timeoutMs: 300_000,
retries: 2,
retryDelayMs: 1500,
cacheDir: null,
logFile: null,
verbose: false,
};
for (let i = 0; i < argv.length; i++) {
const a = argv[i];
const next = () => argv[++i];
switch (a) {
case "--prompt": opts.prompt = next(); break;
case "--prompt-file": opts.promptFile = next(); break;
case "--image": opts.outputPath = next(); break;
case "--aspect": opts.aspect = next(); break;
case "--ref": opts.refImages.push(next()); break;
case "--timeout": opts.timeoutMs = Number(next()); break;
case "--retries": opts.retries = Number(next()); break;
case "--retry-delay": opts.retryDelayMs = Number(next()); break;
case "--cache-dir": opts.cacheDir = next(); break;
case "--log-file": opts.logFile = next(); break;
case "-v":
case "--verbose": opts.verbose = true; break;
case "-h":
case "--help": process.stdout.write(HELP); process.exit(0);
default: throw new GenError("invalid_args", `Unknown argument: ${a}`, false);
}
}
if (!opts.outputPath) throw new GenError("invalid_args", "--image is required", false);
if (opts.prompt && opts.promptFile) {
throw new GenError("invalid_args", "--prompt and --prompt-file are mutually exclusive", false);
}
if (!opts.prompt && !opts.promptFile) {
throw new GenError("invalid_args", "--prompt or --prompt-file required", false);
}
// Resolve every filesystem path to absolute up front, so behavior is
// independent of the caller's cwd. This matters when the wrapper is
// invoked from a skill running in an arbitrary working directory.
const cwd = process.cwd();
const toAbs = (p: string) => (path.isAbsolute(p) ? p : path.resolve(cwd, p));
opts.outputPath = toAbs(opts.outputPath);
if (opts.promptFile) opts.promptFile = toAbs(opts.promptFile);
opts.refImages = opts.refImages.map(toAbs);
if (opts.cacheDir) opts.cacheDir = toAbs(opts.cacheDir);
if (opts.logFile) opts.logFile = toAbs(opts.logFile);
// The output and ref paths are interpolated raw into the agent instruction
// sent to `codex exec --sandbox danger-full-access`. A path containing shell
// metacharacters could be misread by the agent's shell when it cp's the
// result into place. Reject upfront rather than trusting the agent to quote.
assertSafePath("--image path", opts.outputPath);
for (const ref of opts.refImages) assertSafePath("--ref path", ref);
return opts;
}
async function loadPrompt(opts: CliOptions): Promise<string> {
if (opts.prompt) return opts.prompt;
const file = opts.promptFile!;
try {
return await readFile(file, "utf-8");
} catch {
throw new GenError("prompt_file_missing", `Prompt file not found: ${file}`, false);
}
}
function buildInstruction(prompt: string, opts: CliOptions): string {
const refHint = opts.refImages.length > 0
? `\nREFERENCE IMAGES (attached above): ${opts.refImages.length} image(s) provided for style/composition guidance.\n`
: "";
return `You have an internal tool called image_gen for image generation. Use it.
TASK: Generate an image with the spec below, then save to disk.
PROMPT:
${prompt}
ASPECT RATIO: ${opts.aspect}
OUTPUT PATH: ${opts.outputPath}
${refHint}
STEPS:
1. Call image_gen with the prompt and aspect ratio above${opts.refImages.length > 0 ? " (using the attached reference images for guidance)" : ""}.
2. Move or copy the resulting image from Codex default location ($CODEX_HOME/generated_images/...) to: ${opts.outputPath}
3. Verify with: ls -la ${opts.outputPath}
4. Reply with ONLY this JSON line (no markdown fences, no other text):
{"status":"ok","path":"${opts.outputPath}","bytes":<file_size_in_bytes>}
HARD CONSTRAINTS:
- Do NOT use curl, wget, Python, or any external API.
- Do NOT use bash to fabricate an image; only image_gen produces real pixels.
- Use ONLY the image_gen internal tool.`;
}
async function attemptGenerate(
opts: CliOptions,
instruction: string,
attempt: number,
log: JsonLogger,
): Promise<{ bytes: number; threadId: string | null; usage: any; toolCalls: any[] }> {
await log.info("attempt.start", { attempt, output: opts.outputPath, aspect: opts.aspect });
const run = await runCodexExec({
instruction,
timeoutMs: opts.timeoutMs,
refImages: opts.refImages,
});
await log.info("codex.completed", {
duration_ms: run.durationMs,
thread_id: run.threadId,
tool_calls: run.toolCalls.length,
usage: run.usage,
raw_log: run.rawLogPath,
});
// verify: thread id must be present
if (!run.threadId) {
throw new GenError("agent_refused", "No thread id in event stream");
}
// verify: image_gen was actually invoked (check $CODEX_HOME/generated_images/{threadId}/)
const ver = await verifyImageGenWasInvoked(run.threadId);
if (!ver.ok) {
// secondary verify: did tool_calls include cp/mv from generated_images to our target
if (!findCpToTarget(run.toolCalls, opts.outputPath)) {
throw new GenError("no_image_gen_tool_use", `image_gen was not invoked: ${ver.reason}`);
}
}
// verify output
const { bytes } = await verifyOutput(opts.outputPath);
return {
bytes,
threadId: run.threadId,
usage: run.usage,
toolCalls: run.toolCalls.map((tc) => ({ tool: tc.tool, status: tc.status })),
};
}
async function generate(opts: CliOptions, log: JsonLogger): Promise<GenerateResult> {
const startEpoch = Date.now();
const prompt = await loadPrompt(opts);
// Cache lookup
if (opts.cacheDir) {
const key = cacheKey(prompt, opts.aspect, opts.refImages);
const cached = await lookupCache(opts.cacheDir, key);
if (cached) {
await mkdir(path.dirname(opts.outputPath), { recursive: true });
await copyFile(cached, opts.outputPath);
const s = await stat(opts.outputPath);
await log.info("cache.hit", { key, source: cached });
return {
status: "ok",
path: opts.outputPath,
bytes: s.size,
elapsed_seconds: 0,
thread_id: null,
attempts: 0,
cached: true,
usage: null,
tool_calls: [],
};
}
await log.info("cache.miss", { key });
}
// lock to prevent concurrent codex exec
const lockDir = opts.cacheDir ?? path.join(homedir(), ".cache", "baoyu-codex-imagegen");
const lock = new FileLock(path.join(lockDir, "codex-exec.lock"));
try {
await lock.acquire(60_000);
} catch (e) {
throw new GenError("lock_busy", String(e), false);
}
await mkdir(path.dirname(opts.outputPath), { recursive: true });
const instruction = buildInstruction(prompt, opts);
let lastErr: GenError | null = null;
let lastAttempt = 0;
try {
for (let attempt = 1; attempt <= opts.retries + 1; attempt++) {
lastAttempt = attempt;
try {
const result = await attemptGenerate(opts, instruction, attempt, log);
// write to cache
if (opts.cacheDir) {
const key = cacheKey(prompt, opts.aspect, opts.refImages);
await storeCache(opts.cacheDir, key, opts.outputPath);
await log.info("cache.stored", { key });
}
return {
status: "ok",
path: opts.outputPath,
bytes: result.bytes,
elapsed_seconds: Math.round((Date.now() - startEpoch) / 1000),
thread_id: result.threadId,
attempts: attempt,
cached: false,
usage: result.usage,
tool_calls: result.toolCalls,
};
} catch (e) {
lastErr = e instanceof GenError ? e : new GenError("spawn_failed", String(e));
await log.warn("attempt.failed", {
attempt,
kind: lastErr.kind,
retryable: lastErr.retryable,
error: lastErr.message,
});
if (!lastErr.retryable || attempt > opts.retries) break;
const wait = opts.retryDelayMs * Math.pow(2, attempt - 1);
await log.info("retry.wait", { wait_ms: wait, next_attempt: attempt + 1 });
await delay(wait);
}
}
} finally {
await lock.release();
}
const err = lastErr ?? new GenError("spawn_failed", "Unknown failure");
err.attempts = lastAttempt;
throw err;
}
async function main() {
let opts: CliOptions;
try {
opts = parseArgs(process.argv.slice(2));
} catch (e) {
const err = e instanceof GenError ? e : new GenError("invalid_args", String(e), false);
process.stderr.write(`Error: ${err.message}\n`);
process.exit(2);
}
const log = new JsonLogger(opts.logFile, opts.verbose);
await log.info("start", { output: opts.outputPath, aspect: opts.aspect, refs: opts.refImages.length });
try {
const result = await generate(opts, log);
await log.info("done", { bytes: result.bytes, attempts: result.attempts, cached: result.cached });
process.stdout.write(JSON.stringify(result) + "\n");
process.exit(0);
} catch (e) {
const err = e instanceof GenError ? e : new GenError("spawn_failed", String(e));
await log.error("failed", { kind: err.kind, error: err.message, attempts: err.attempts ?? 0 });
const out: GenerateResult = {
status: "error",
path: opts.outputPath,
bytes: 0,
elapsed_seconds: 0,
thread_id: null,
attempts: err.attempts ?? 0,
cached: false,
usage: null,
tool_calls: [],
error: err.message,
error_kind: err.kind,
};
process.stdout.write(JSON.stringify(out) + "\n");
process.exit(1);
}
}
main();
@@ -0,0 +1,64 @@
import type { CodexRunResult, ToolCall, TokenUsage } from "./types.ts";
export function parseEventStream(raw: string): Omit<CodexRunResult, "rawLogPath" | "durationMs"> {
const lines = raw.split("\n").filter((l) => l.trim().length > 0);
let threadId: string | null = null;
let agentMessage: string | null = null;
let usage: TokenUsage | null = null;
const toolCallsById = new Map<string, ToolCall>();
for (const line of lines) {
let event: any;
try {
event = JSON.parse(line);
} catch {
continue;
}
const type = event?.type;
if (type === "thread.started") {
threadId = event.thread_id ?? null;
} else if (type === "item.started" || type === "item.completed") {
const item = event.item;
if (!item?.id) continue;
const tc: ToolCall = {
id: item.id,
tool: deriveToolName(item),
status: item.status ?? (type === "item.completed" ? "completed" : "in_progress"),
command: item.command,
};
toolCallsById.set(item.id, tc);
if (item.type === "agent_message" && type === "item.completed") {
agentMessage = String(item.text ?? "");
}
} else if (type === "turn.completed") {
const u = event.usage;
if (u) {
usage = {
input: u.input_tokens ?? 0,
cached_input: u.cached_input_tokens ?? 0,
output: u.output_tokens ?? 0,
reasoning: u.reasoning_output_tokens ?? 0,
};
}
}
}
return {
threadId,
toolCalls: Array.from(toolCallsById.values()),
agentMessage,
usage,
};
}
function deriveToolName(item: any): string {
if (item.type === "command_execution") return "shell";
if (item.type === "agent_message") return "agent_message";
if (item.type === "image_gen" || item.type === "image_generation") return "image_gen";
if (typeof item.tool === "string") return item.tool;
return item.type ?? "unknown";
}
export function hasImageGenInvocation(toolCalls: ToolCall[]): boolean {
return toolCalls.some((tc) => tc.tool === "image_gen");
}
@@ -0,0 +1,81 @@
import { spawn } from "node:child_process";
import { writeFile, mkdtemp } from "node:fs/promises";
import { tmpdir } from "node:os";
import path from "node:path";
import { GenError, type CodexRunResult } from "./types.ts";
import { parseEventStream } from "./parser.ts";
export interface SpawnInput {
instruction: string;
timeoutMs: number;
refImages?: string[];
}
export async function runCodexExec(input: SpawnInput): Promise<CodexRunResult> {
const start = Date.now();
const logDir = await mkdtemp(path.join(tmpdir(), "codex-imggen-"));
const rawLogPath = path.join(logDir, "stream.jsonl");
// --skip-git-repo-check: lets the wrapper run from non-git cwds
// (e.g. /tmp, or a skill installed under ~/.claude/plugins/...).
// Without it, codex refuses with "Not inside a trusted directory".
const args = [
"exec",
"--json",
"--sandbox",
"danger-full-access",
"--skip-git-repo-check",
];
for (const img of input.refImages ?? []) {
args.push("--image", img);
}
args.push("-");
let timedOut = false;
const child = spawn("codex", args, { stdio: ["pipe", "pipe", "pipe"] });
let stdout = "";
let stderr = "";
child.stdout.on("data", (chunk) => {
stdout += chunk.toString();
});
child.stderr.on("data", (chunk) => {
stderr += chunk.toString();
});
child.stdin.write(input.instruction);
child.stdin.end();
const timer = setTimeout(() => {
timedOut = true;
child.kill("SIGTERM");
setTimeout(() => child.kill("SIGKILL"), 2000);
}, input.timeoutMs);
const exit = await new Promise<{ code: number | null; signal: NodeJS.Signals | null }>((resolve) => {
child.on("close", (code, signal) => resolve({ code, signal }));
});
clearTimeout(timer);
await writeFile(rawLogPath, stdout + (stderr ? `\n--- stderr ---\n${stderr}` : ""));
if (timedOut) {
throw new GenError("timeout", `codex exec exceeded ${input.timeoutMs}ms (log: ${rawLogPath})`);
}
if (exit.code !== 0) {
if (stderr.includes("command not found") || stderr.includes("not found: codex")) {
throw new GenError("codex_not_installed", "codex CLI not installed", false);
}
throw new GenError(
"spawn_failed",
`codex exec exited ${exit.code} signal=${exit.signal} (log: ${rawLogPath})`,
);
}
const parsed = parseEventStream(stdout);
return {
...parsed,
rawLogPath,
durationMs: Date.now() - start,
};
}
@@ -0,0 +1,79 @@
export interface CliOptions {
prompt: string;
promptFile: string | null;
outputPath: string;
aspect: string;
refImages: string[];
timeoutMs: number;
retries: number;
retryDelayMs: number;
cacheDir: string | null;
logFile: string | null;
verbose: boolean;
}
export interface ToolCall {
id: string;
tool: string;
status: string;
command?: string;
}
export interface TokenUsage {
input: number;
cached_input: number;
output: number;
reasoning: number;
}
export interface CodexRunResult {
threadId: string | null;
toolCalls: ToolCall[];
agentMessage: string | null;
usage: TokenUsage | null;
rawLogPath: string;
durationMs: number;
}
export interface GenerateResult {
status: "ok" | "error";
path: string;
bytes: number;
elapsed_seconds: number;
thread_id: string | null;
attempts: number;
cached: boolean;
usage: TokenUsage | null;
tool_calls: { tool: string; status: string }[];
error?: string;
error_kind?: ErrorKind;
}
export type ErrorKind =
| "codex_not_installed"
| "invalid_args"
| "prompt_file_missing"
| "spawn_failed"
| "timeout"
| "no_image_gen_tool_use"
| "output_missing"
| "invalid_png"
| "agent_refused"
| "lock_busy";
export const RETRYABLE: ReadonlySet<ErrorKind> = new Set([
"spawn_failed",
"timeout",
"no_image_gen_tool_use",
"output_missing",
"invalid_png",
"agent_refused",
]);
export class GenError extends Error {
attempts?: number;
constructor(public kind: ErrorKind, message: string, public retryable?: boolean) {
super(message);
this.retryable = retryable ?? RETRYABLE.has(kind);
}
}
@@ -0,0 +1,55 @@
import { stat, readdir } from "node:fs/promises";
import { homedir } from "node:os";
import path from "node:path";
import { GenError } from "./types.ts";
import type { ToolCall } from "./types.ts";
const PNG_MAGIC = Buffer.from([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a]);
export function codexHome(): string {
return process.env.CODEX_HOME ?? path.join(homedir(), ".codex");
}
export async function verifyImageGenWasInvoked(threadId: string | null): Promise<{ ok: boolean; reason?: string }> {
if (!threadId) return { ok: false, reason: "no thread id" };
const dir = path.join(codexHome(), "generated_images", threadId);
try {
const entries = await readdir(dir);
const pngs = entries.filter((e) => e.toLowerCase().endsWith(".png"));
if (pngs.length === 0) return { ok: false, reason: `no PNG in ${dir}` };
return { ok: true };
} catch (e: any) {
return { ok: false, reason: `cannot read ${dir}: ${e?.code ?? e?.message}` };
}
}
export function findCpToTarget(toolCalls: ToolCall[], target: string): boolean {
return toolCalls.some(
(tc) =>
tc.tool === "shell" &&
typeof tc.command === "string" &&
(tc.command.includes(target) || tc.command.includes(path.basename(target))) &&
/\b(cp|mv|cat)\b/.test(tc.command) &&
tc.command.includes("generated_images"),
);
}
export async function verifyOutput(outputPath: string): Promise<{ bytes: number }> {
let s;
try {
s = await stat(outputPath);
} catch {
throw new GenError("output_missing", `Output file not created: ${outputPath}`);
}
if (s.size < 1000) {
throw new GenError("invalid_png", `Output file too small (${s.size} bytes)`);
}
const file = Bun.file(outputPath);
const head = new Uint8Array(await file.slice(0, 8).arrayBuffer());
for (let i = 0; i < PNG_MAGIC.length; i++) {
if (head[i] !== PNG_MAGIC[i]) {
throw new GenError("invalid_png", `Output is not a valid PNG (magic mismatch)`);
}
}
return { bytes: s.size };
}