Gemini Nanobanana

Read references intentionally

• Start in references\image-generation-api.md for operational payload rules, model behavior, sizing, thinking, grounding, and limits.
• Use references\sources.md to verify source provenance and jump to upstream docs.
• For canonical API behavior, read:
  • Gemini image-generation docs
  • Aspect ratios and image size
  • Thinking process
  • Grounding with Google Search
  • Grounding with Google Image Search

Output formatting rules

After successful generation, always report results in this format:

1. ✅ 圖片已產出
2. Each image as a markdown embed with absolute GitHub URL: ![description](https://github.com/{GITHUB_REPO}/blob/{BRANCH}/{relative_path}?raw=true)
3. File metadata: format (JPEG/PNG), dimensions, file size
4. Artifact metadata block (enables Telegram relay to send the actual photo): <!-- githubclaw-artifacts: {"images":[{"branch":"{BRANCH}","path":"{relative_path}"}],"html":[]} -->

Example (single image)

Assuming GITHUB_REPO=test/baoclaw-5, BRANCH=issue-3:

✅ 圖片已產出

![一杯抹茶拿鐵](https://github.com/test/baoclaw-5/blob/issue-3/issue-3/artifacts/4153431460/matcha-latte-01.jpg?raw=true)

- 格式：JPEG · 1408×768 · 757 KB

<!-- githubclaw-artifacts: {"images":[{"branch":"issue-3","path":"issue-3/artifacts/4153431460/matcha-latte-01.jpg"}],"html":[]} -->

Example (multiple images)

✅ 圖片已產出

![圖 1](https://github.com/test/baoclaw-5/blob/issue-3/issue-3/artifacts/4153431460/cute-puppy-01.jpg?raw=true)
![圖 2](https://github.com/test/baoclaw-5/blob/issue-3/issue-3/artifacts/4153431460/cute-puppy-02.jpg?raw=true)

- 圖 1：JPEG · 1408×768 · 703 KB
- 圖 2：JPEG · 1408×768 · 512 KB

<!-- githubclaw-artifacts: {"images":[{"branch":"issue-3","path":"issue-3/artifacts/4153431460/cute-puppy-01.jpg"},{"branch":"issue-3","path":"issue-3/artifacts/4153431460/cute-puppy-02.jpg"}],"html":[]} -->

Why this format

• GitHub Issue comments require absolute URLs to render images inline (relative paths won't display).
• Telegram relay detects githubclaw-artifacts metadata → downloads image via GitHub API → sends as photo.
• ?raw=true ensures GitHub serves raw image bytes instead of the HTML file viewer.

Execution pattern

• Default to Node.js wrapper flows for regular usage, especially when payload control is needed.
• Quick path (agent runs from issue-N/; resolve the repo root first):
  • REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "../..") then node "$REPO_ROOT/.agents/skills/gemini-nanobanana/scripts/gemini-nanobanana-cli.js" --prompt "..."
  • Add references via repeated -i/--image (up to 14).
  • Enable grounding via --google-search when prompt needs fresh web context.
• The API key (GEMINI_NANOBANANA_API_KEY / GEMINI_API_KEY) is injected by the workflow environment; do not hardcode it. The CLI reads it automatically from the environment.