feat: add codex-imagegen backend for non-Codex runtimes

Implements the preferred_image_backend: codex-imagegen config key
already referenced in several SKILL.md files but with no corresponding
backend. Bridges non-Codex runtimes (Claude Code, etc.) to Codex CLI's
built-in image_gen tool via 'codex exec'. Uses the user's Codex
subscription — no OPENAI_API_KEY required.

Reliability:
- Retry with exponential backoff (default 2 retries, configurable)
- 9 classified error kinds (retryable vs non-retryable)
- Node child_process timeout with SIGTERM→SIGKILL ladder

Correctness:
- Verifies image_gen was actually invoked (not bypassed) by checking
  $CODEX_HOME/generated_images/{thread_id}/ for a PNG
- PNG magic byte validation
- Output file size sanity check

Observability:
- Structured JSONL logging with --log-file
- Verbose stderr mode with --verbose
- Returns thread_id, tool_calls, token usage in result JSON
- Raw codex event stream preserved per attempt for debugging

Efficiency:
- Idempotency cache via --cache-dir (sha256 of prompt+aspect+refs)
- Cache hit returns in <0.3s vs 50-90s cold

Features:
- --ref reference images (repeatable, passed through to codex exec --image)
- --retries, --retry-delay, --timeout all configurable
- File lock serializes concurrent invocations

Testing:
- 16 Bun unit tests across parser, cache, validator
- Path-filtered CI workflow at .github/workflows/codex-imagegen-tests.yml
- Composes with existing test.yml without conflicts

Architecture:
- scripts/codex-imagegen.sh: thin bash entrypoint (bun → npx -y bun fallback)
- scripts/codex-imagegen/: TypeScript module
  - main.ts (orchestrator), types.ts (CliOptions/GenerateResult/GenError),
    spawn.ts (child_process), parser.ts (JSONL events), validator.ts
    (image_gen check + PNG magic), cache.ts (sha256 cache + FileLock),
    logger.ts (JSONL structured logger)

Trade-offs documented in docs/codex-imagegen-backend.md:
- 5-10x slower than direct OpenAI API (or near-free on cache hit)
- ToS gray area: image_gen is documented for interactive use; non-
  interactive invocation via codex exec is not explicitly addressed.
  Suitable for personal low-volume use; users are responsible for
  ensuring their usage complies with applicable terms of service.
This commit is contained in:
Yelban
2026-05-20 00:50:24 +08:00
parent 5d2a39c636
commit e98fa33bc2
14 changed files with 1253 additions and 0 deletions
+72
View File
@@ -0,0 +1,72 @@
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");
const args = ["exec", "--json", "--sandbox", "danger-full-access"];
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,
};
}