refactor(codex-imagegen): extract backend to packages/baoyu-codex-imagegen workspace

Move the codex-imagegen wrapper out of scripts/ into its own workspace package alongside baoyu-md, baoyu-chrome-cdp, and baoyu-fetch. Drop the bash shim — src/main.ts now carries a `#\!/usr/bin/env bun` shebang and serves as the sole entrypoint. Add scripts/sync-codex-imagegen.sh so skills/baoyu-image-gen/scripts/codex-imagegen/ can be regenerated from packages/baoyu-codex-imagegen/src/ for skill self-containment. Update CLAUDE.md, docs/codex-imagegen-backend.md, and the CI workflow paths accordingly.
2026-07-12 05:51:44 +08:00 · 2026-05-25 00:18:16 -05:00
parent 66160abb9f
commit 23fac03691
17 changed files with 252 additions and 54 deletions
@@ -3,13 +3,11 @@ name: codex-imagegen tests
 on:
  push:
    paths:
-      - 'scripts/codex-imagegen/**'
-      - 'scripts/codex-imagegen.sh'
+      - 'packages/baoyu-codex-imagegen/**'
      - '.github/workflows/codex-imagegen-tests.yml'
  pull_request:
    paths:
-      - 'scripts/codex-imagegen/**'
-      - 'scripts/codex-imagegen.sh'
+      - 'packages/baoyu-codex-imagegen/**'
      - '.github/workflows/codex-imagegen-tests.yml'
  workflow_dispatch:

@@ -30,11 +28,11 @@ jobs:
        run: bun --version

      - name: Run unit tests
-        working-directory: scripts/codex-imagegen
+        working-directory: packages/baoyu-codex-imagegen
        run: bun test

      - name: Bundle smoke test (catches import/syntax errors)
-        run: bun build --target=node scripts/codex-imagegen/main.ts --outfile /tmp/main-build.js
+        run: bun build --target=node packages/baoyu-codex-imagegen/src/main.ts --outfile /tmp/main-build.js

      - name: Help output smoke test
-        run: bun scripts/codex-imagegen/main.ts --help
+        run: bun packages/baoyu-codex-imagegen/src/main.ts --help
@@ -68,19 +68,21 @@ Skills that render images MUST declare the backend-selection convention **inline

 ### `codex-imagegen` Backend

-A backend for non-Codex runtimes (e.g., Claude Code) that generates images by spawning `codex exec --json --sandbox danger-full-access` and delegating to Codex CLI's built-in `image_gen` tool. Uses the user's Codex subscription — no `OPENAI_API_KEY` required.
+A backend for non-Codex runtimes (e.g., Claude Code) that generates images by spawning `codex exec --json --sandbox danger-full-access` and delegating to Codex CLI's built-in `image_gen` tool. Uses the user's Codex subscription — no `OPENAI_API_KEY` required. Lives under [packages/baoyu-codex-imagegen](packages/baoyu-codex-imagegen) so it follows the same workspace layout as other shared packages.

-Invoke via:
+Invoke via (TS entrypoint with `#!/usr/bin/env bun` shebang):

 ```bash
-./scripts/codex-imagegen.sh \
+bun packages/baoyu-codex-imagegen/src/main.ts \
  --image <output.png> \
  --prompt-file prompts/01-cover.md \
  --aspect 16:9 \
  --cache-dir ~/.cache/baoyu-codex-imagegen
 ```

-Stdout emits a single JSON line: `{"status":"ok","path":...,"bytes":N,...}`. On failure, `{"status":"error","error_kind":...}`. Skills route here by setting `preferred_image_backend: codex-imagegen` in EXTEND.md. Full reference: [docs/codex-imagegen-backend.md](docs/codex-imagegen-backend.md).
+Without bun installed: `npx -y bun packages/baoyu-codex-imagegen/src/main.ts …`.
+
+Stdout emits a single JSON line: `{"status":"ok","path":...,"bytes":N,...}`. On failure, `{"status":"error","error_kind":...}`. Skills route here by setting `preferred_image_backend: codex-imagegen` in EXTEND.md, or by running `baoyu-image-gen --provider codex-cli` (which spawns the same wrapper internally). Full reference: [docs/codex-imagegen-backend.md](docs/codex-imagegen-backend.md).

 ## Release Process

@@ -35,13 +35,13 @@ codex login            # signs in with your OpenAI account (subscription)
 codex --version        # confirm >= 0.130
 ```

-`bun` is preferred for running the wrapper. On macOS:
+`bun` is required for running the wrapper. On macOS:

 ```bash
 brew install oven-sh/bun/bun
 ```

-If `bun` is missing, the shell entrypoint falls back to `npx -y bun`.
+If `bun` is not on `PATH`, fall back to `npx -y bun packages/baoyu-codex-imagegen/src/main.ts …`.

 ## Usage

@@ -49,20 +49,32 @@ If `bun` is missing, the shell entrypoint falls back to `npx -y bun`.

 ```bash
 # Inline prompt
-./scripts/codex-imagegen.sh \
+bun packages/baoyu-codex-imagegen/src/main.ts \
  --image /tmp/cat.png \
  --prompt "A friendly orange cat, watercolor"

 # Prompt from file
-./scripts/codex-imagegen.sh \
+bun packages/baoyu-codex-imagegen/src/main.ts \
  --image cover.png \
  --prompt-file prompts/01-cover.md \
  --aspect 16:9

 # Verbose mode for debugging
-./scripts/codex-imagegen.sh -v --image dog.png --prompt "A corgi" --aspect 1:1
+bun packages/baoyu-codex-imagegen/src/main.ts -v --image dog.png --prompt "A corgi" --aspect 1:1
 ```

+### Through `baoyu-image-gen`
+
+```bash
+${BUN_X} skills/baoyu-image-gen/scripts/main.ts \
+  --provider codex-cli \
+  --prompt "A friendly orange cat, watercolor" \
+  --image /tmp/cat.png \
+  --ar 1:1
+```
+
+The `codex-cli` provider spawns the bundled `codex-imagegen` TS entrypoint internally and surfaces its retry/cache machinery through baoyu-image-gen's standard CLI + batch flow.
+
 On success, stdout emits a single JSON line:

 ```json
@@ -80,7 +92,7 @@ Image-generating skills (e.g., `baoyu-cover-image`, `baoyu-article-illustrator`)
 preferred_image_backend: codex-imagegen
 ```

-When the LLM runs the skill, it reads the preference and — guided by the `### codex-imagegen Backend` section in `CLAUDE.md` — invokes `scripts/codex-imagegen.sh`.
+When the LLM runs the skill, it reads the preference and — guided by the `### codex-imagegen Backend` section in `CLAUDE.md` — invokes `bun packages/baoyu-codex-imagegen/src/main.ts`.

 > **Note**: The integration is mediated by the LLM reading `CLAUDE.md`. It is not a hard binding. If a skill does not route to the backend automatically, mentioning it explicitly in the prompt works.

@@ -191,24 +203,26 @@ On failure, exit code is `1` and the JSON contains `error` and `error_kind`:
 ## Architecture

 ```
-scripts/codex-imagegen.sh        # thin bash entrypoint
-scripts/codex-imagegen/
-├── main.ts        # parseArgs → cache → lock → retry loop → emit JSON
-├── types.ts       # CliOptions, GenerateResult, GenError, ErrorKind
-├── spawn.ts       # spawn codex exec --json --sandbox danger-full-access
-├── parser.ts      # parse JSONL event stream → toolCalls, usage, thread_id
-├── validator.ts   # verify image_gen invocation + PNG magic + file size
-├── cache.ts       # cacheKey(sha256), FileLock, lookup/store
-├── logger.ts      # JsonLogger (verbose stderr + JSONL file)
-├── parser.test.ts
-├── cache.test.ts
-└── validator.test.ts
+packages/baoyu-codex-imagegen/
+├── src/
+│   ├── main.ts             # parseArgs → cache → lock → retry loop → emit JSON (`#!/usr/bin/env bun`)
+│   ├── types.ts            # CliOptions, GenerateResult, GenError, ErrorKind
+│   ├── spawn.ts            # spawn codex exec --json --sandbox danger-full-access
+│   ├── parser.ts           # parse JSONL event stream → toolCalls, usage, thread_id
+│   ├── validator.ts        # verify image_gen invocation + PNG magic + file size
+│   ├── cache.ts            # cacheKey(sha256), FileLock, lookup/store
+│   ├── logger.ts           # JsonLogger (verbose stderr + JSONL file)
+│   ├── parser.test.ts
+│   ├── cache.test.ts
+│   └── validator.test.ts
+├── package.json            # workspace package: `bin` → `src/main.ts`, no build step
+└── README.md
 ```

 Run tests:

 ```bash
-cd scripts/codex-imagegen && bun test
+cd packages/baoyu-codex-imagegen && bun test
 ```

 ## Internal Flow
@@ -216,7 +230,7 @@ cd scripts/codex-imagegen && bun test
 ```mermaid
 flowchart LR
    CC[Claude Code / any caller]
-    WRAPPER[scripts/codex-imagegen.sh]
+    WRAPPER[bun packages/baoyu-codex-imagegen/<br/>src/main.ts]
    CODEX["codex exec --json<br/>--sandbox danger-full-access"]
    AGENT[Codex agent]
    TOOL[image_gen built-in tool]
@@ -239,18 +253,20 @@ flowchart LR

 ## Design Decisions

-1. **Bash entrypoint + TypeScript implementation** — the shell wrapper picks the runtime (`bun` preferred, falling back to `npx -y bun`); TypeScript handles the orchestration, parsing, retry, cache, and logging. This mirrors the project's existing `scripts/*.mjs` and `skills/<skill>/scripts/main.ts` pattern.
+1. **Pure TypeScript entrypoint** — `src/main.ts` carries a `#!/usr/bin/env bun` shebang and is the sole entry. There is no shell shim: callers either invoke `bun src/main.ts …` directly, run the file as an executable (when `bun` is on `PATH`), or fall back to `npx -y bun src/main.ts …`. This matches the project's `skills/<skill>/scripts/main.ts` convention.
 2. **`--sandbox danger-full-access`** — necessary so the spawned agent can `cp`/`mv` the rendered PNG out of `$CODEX_HOME/generated_images/` to the user-specified path. Standard sandboxes block this.
 3. **Parse the JSONL event stream** — the final `agent_message` and intermediate `command_execution` events let the wrapper verify what actually happened (was `image_gen` called? did `cp` reach the right destination?), which is far more reliable than scraping freeform stdout.
-4. **Infrastructure, not a skill** — this backend is a CLI utility that skills route to via `preferred_image_backend`. It belongs in `scripts/`, not `skills/`, because it has no `SKILL.md` and is never loaded directly by an agent.
+4. **Shared package, not a skill** — this backend is a CLI utility that skills route to via `preferred_image_backend` and that `baoyu-image-gen --provider codex-cli` spawns internally. It lives under `packages/` alongside the other shared workspaces (`baoyu-md`, `baoyu-chrome-cdp`, `baoyu-fetch`) because it has no `SKILL.md` and is never loaded directly by an agent.
 5. **File lock instead of internal queue** — keeps the implementation small and works across multiple shell sessions or processes invoking the same wrapper concurrently.

 ## Related Files

 | File | Role |
 |------|------|
-| `scripts/codex-imagegen.sh` | CLI entrypoint |
-| `scripts/codex-imagegen/` | TypeScript implementation |
+| `packages/baoyu-codex-imagegen/src/main.ts` | TypeScript CLI entrypoint (`#!/usr/bin/env bun`) |
+| `packages/baoyu-codex-imagegen/src/` | TypeScript implementation |
+| `packages/baoyu-codex-imagegen/package.json` | Workspace manifest |
+| `skills/baoyu-image-gen/scripts/providers/codex-cli.ts` | Provider adapter that lets `baoyu-image-gen --provider codex-cli` spawn this wrapper |
 | `docs/codex-imagegen-backend.md` | This document |
 | `CLAUDE.md` | Tells LLMs how to invoke this backend |
 | `.github/workflows/codex-imagegen-tests.yml` | CI unit tests |
@@ -0,0 +1,102 @@
+# baoyu-codex-imagegen
+
+Generate images via Codex CLI's built-in `image_gen` tool from non-Codex runtimes (e.g., Claude Code). The wrapper spawns `codex exec --json` and lets the user's existing Codex subscription drive image generation — **no `OPENAI_API_KEY` required**.
+
+This package implements the `preferred_image_backend: codex-imagegen` config key referenced across the `baoyu-skills` plugin and is the engine behind `baoyu-image-gen --provider codex-cli`.
+
+## Layout
+
+```
+packages/baoyu-codex-imagegen/
+├── src/
+│   ├── main.ts             # CLI orchestrator (executable via `#!/usr/bin/env bun`)
+│   ├── spawn.ts            # codex exec child-process wrapper
+│   ├── parser.ts           # JSONL event-stream parser
+│   ├── validator.ts        # Output PNG / image_gen-invocation verification
+│   ├── cache.ts            # SHA256 idempotency cache + file lock
+│   ├── logger.ts           # Structured JSONL logging
+│   ├── types.ts            # Shared types and `GenError`
+│   └── *.test.ts           # Bun unit tests
+└── package.json            # `bin` points to `src/main.ts`
+```
+
+## Prerequisites
+
+```bash
+npm install -g @openai/codex
+codex login            # signs in with your OpenAI account (subscription)
+codex --version        # confirm >= 0.130
+```
+
+`bun` is required for running the wrapper:
+
+```bash
+brew install oven-sh/bun/bun
+```
+
+If `bun` is not on `PATH`, `npx -y bun src/main.ts …` works as a fallback.
+
+## Usage
+
+```bash
+# Inline prompt (executes via shebang once bun is on PATH)
+./src/main.ts \
+  --image /tmp/cat.png \
+  --prompt "A friendly orange cat, watercolor"
+
+# Or invoke bun explicitly
+bun src/main.ts \
+  --image cover.png \
+  --prompt-file prompts/01-cover.md \
+  --aspect 16:9 \
+  --cache-dir ~/.cache/baoyu-codex-imagegen
+
+# Without bun installed
+npx -y bun src/main.ts --image cover.png --prompt "..."
+```
+
+Stdout emits a single JSON line:
+
+```json
+{"status":"ok","path":"…","bytes":1234567,"elapsed_seconds":62,"thread_id":"…","attempts":1,"cached":false,"usage":{…}}
+```
+
+On failure:
+
+```json
+{"status":"error","path":"…","bytes":0,"error":"…","error_kind":"timeout"}
+```
+
+`error_kind` values: `codex_not_installed`, `invalid_args`, `prompt_file_missing`, `spawn_failed`, `timeout`, `no_image_gen_tool_use`, `output_missing`, `invalid_png`, `agent_refused`, `lock_busy`.
+
+## Options
+
+| Flag | Description |
+|---|---|
+| `--image <path>` | Output PNG path (required) |
+| `--prompt <text>` | Prompt text |
+| `--prompt-file <path>` | Read prompt from file (mutually exclusive with `--prompt`) |
+| `--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 structured JSONL log |
+| `-v, --verbose` | Verbose stderr logging |
+| `-h, --help` | Show help |
+
+## Test
+
+```bash
+cd packages/baoyu-codex-imagegen
+bun test
+```
+
+## Trade-offs
+
+- 5–10× slower than direct OpenAI API calls (except on cache hits)
+- Uses your Codex subscription — programmatic use of `codex exec` falls into the same terms as interactive use
+- Requires `codex` CLI and active login session
+
+See [`docs/codex-imagegen-backend.md`](../../docs/codex-imagegen-backend.md) for the full background.
@@ -0,0 +1,39 @@
+{
+  "name": "baoyu-codex-imagegen",
+  "version": "0.1.0",
+  "type": "module",
+  "description": "Generate images via Codex CLI's built-in image_gen tool from non-Codex runtimes (Claude Code, Hermes, …).",
+  "bin": {
+    "codex-imagegen": "./src/main.ts"
+  },
+  "files": [
+    "src/**/*.ts",
+    "!src/**/*.test.ts"
+  ],
+  "exports": {
+    ".": {
+      "types": "./src/main.ts",
+      "default": "./src/main.ts"
+    },
+    "./src/*": "./src/*"
+  },
+  "scripts": {
+    "test": "bun test",
+    "smoke": "bun src/main.ts --help"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/JimLiu/baoyu-skills.git",
+    "directory": "packages/baoyu-codex-imagegen"
+  },
+  "bugs": {
+    "url": "https://github.com/JimLiu/baoyu-skills/issues"
+  },
+  "homepage": "https://github.com/JimLiu/baoyu-skills/tree/main/packages/baoyu-codex-imagegen#readme",
+  "publishConfig": {
+    "access": "public"
+  },
+  "engines": {
+    "bun": ">=1.2.0"
+  }
+}
@@ -1,3 +1,4 @@
+#!/usr/bin/env bun
 import { readFile, mkdir, copyFile, stat } from "node:fs/promises";
 import { homedir } from "node:os";
 import path from "node:path";
@@ -1,19 +0,0 @@
-#!/bin/bash
-# codex-imagegen: generate images via Codex CLI's built-in image_gen tool
-# Thin shell wrapper — implementation in codex-imagegen/main.ts (Bun TypeScript)
-#
-# Usage: ./codex-imagegen.sh --help
-
-set -euo pipefail
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-
-if command -v bun &>/dev/null; then
-    BUN_X="bun"
-elif command -v npx &>/dev/null; then
-    BUN_X="npx -y bun"
-else
-    echo "Error: bun or npx required. Install: brew install oven-sh/bun/bun" >&2
-    exit 1
-fi
-
-exec $BUN_X "$SCRIPT_DIR/codex-imagegen/main.ts" "$@"
@@ -0,0 +1,59 @@
+#!/bin/bash
+# Sync packages/baoyu-codex-imagegen/src/*.ts (excluding tests) into
+# skills/baoyu-image-gen/scripts/codex-imagegen/ so the skill stays
+# self-contained (no `../../../../packages/...` lookups at runtime).
+#
+# Run this whenever packages/baoyu-codex-imagegen/src/ changes,
+# and always before tagging a release.
+
+set -euo pipefail
+
+REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+SRC_DIR="$REPO_ROOT/packages/baoyu-codex-imagegen/src"
+DST_DIR="$REPO_ROOT/skills/baoyu-image-gen/scripts/codex-imagegen"
+
+if [[ ! -d "$SRC_DIR" ]]; then
+  echo "Error: source dir missing: $SRC_DIR" >&2
+  exit 1
+fi
+
+mkdir -p "$DST_DIR"
+
+changed=0
+for f in cache.ts logger.ts main.ts parser.ts spawn.ts types.ts validator.ts; do
+  src="$SRC_DIR/$f"
+  dst="$DST_DIR/$f"
+  if [[ ! -f "$src" ]]; then
+    echo "Error: missing source file: $src" >&2
+    exit 1
+  fi
+  if [[ ! -f "$dst" ]] || ! cmp -s "$src" "$dst"; then
+    cp "$src" "$dst"
+    echo "synced: $f"
+    changed=$((changed + 1))
+  fi
+done
+
+chmod +x "$DST_DIR/main.ts"
+
+# Drop any stale .ts files in DST that don't exist in SRC.
+for dst in "$DST_DIR"/*.ts; do
+  [[ -e "$dst" ]] || continue
+  name="$(basename "$dst")"
+  case "$name" in
+    *.test.ts) rm -f "$dst"; echo "removed test artifact: $name" ;;
+    *)
+      if [[ ! -f "$SRC_DIR/$name" ]]; then
+        rm -f "$dst"
+        echo "removed stale: $name"
+        changed=$((changed + 1))
+      fi
+      ;;
+  esac
+done
+
+if [[ "$changed" -eq 0 ]]; then
+  echo "codex-imagegen sync: up to date"
+else
+  echo "codex-imagegen sync: $changed file(s) updated"
+fi