Two improvements so the wrapper works the same regardless of caller cwd
or whether cwd is a git repo:
1. main.ts: resolve all filesystem path args (--prompt-file, --ref,
--cache-dir, --log-file) to absolute paths up front. Previously only
--image was resolved. Agents passing relative paths from arbitrary
working directories (e.g. when SKILL.md is interpreted from a plugin
install dir) now produce correct file lookups.
2. spawn.ts: pass --skip-git-repo-check to 'codex exec'. Without it,
codex refuses to run outside a trusted directory:
'Not inside a trusted directory and --skip-git-repo-check was not
specified.' This made the wrapper fail when invoked from /tmp or
from a non-git project tree.
3. baoyu-cover-image/SKILL.md: explicit path resolution note —
scripts/codex-imagegen.sh lives at plugin/repo root (not shell
cwd-relative). From the skill base directory it is at
'../../scripts/codex-imagegen.sh'. Agents should resolve to an
absolute path before invoking.
Verified:
- 16 unit tests pass
- e2e from /tmp (non-git, relative-path args) → 45s, 1.6MB PNG, status:ok
Composes with the existing cover-image wiring (commit e3932e4).
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.
Jim Liu 宝玉
Yelban