mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
123cf62a48
## Why Image edits should use the exact images selected by the model instead of inferring edit inputs from conversation history. ## What changed - Replaced the image tool's `action` argument with optional `referenced_image_paths`. - Treats omitted or empty references as generation and populated references as editing. - Reads referenced absolute image paths and packages them as image data URLs for the edit request. - Removed the previous history-selection and image-count heuristics. - Updated direct and code-mode tool instructions and calls. - Added an app-server integration test covering an attached image routed to the image edit endpoint. ## Validation - Tested end-to-end on local `just codex` with copy pasted image, attached image, etc. - `just test -p codex-image-generation-extension` - `just test -p codex-app-server standalone_image_edit_uses_attached_model_visible_image` - `just fix -p codex-image-generation-extension` - `just bazel-lock-check`
1.7 KiB
1.7 KiB
The image_gen.imagegen tool enables image generation from descriptions and editing of existing images based on specific instructions. Use it when:
- The user requests an image based on a scene description, such as a diagram, portrait, comic, meme, or any other visual.
- The user wants to modify an attached or previously generated image with specific changes, including adding or removing elements, altering colors, improving quality/resolution, or transforming the style (e.g., cartoon, oil painting).
Guidelines:
- In code mode, pass the result to
generatedImage(result). - Omit both
referenced_image_pathsandnum_last_images_to_includewhen generating a brand new image. - For edits, use
referenced_image_pathswhen every target image has a local file path. - If you have not seen a local image yet, use
view_imageto inspect it before editing. - Use
num_last_images_to_includeonly when at least one target image has no local file path. - Set
num_last_images_to_includeto the smallest number of recent conversation images that includes every target image, up to 5. - Never provide both
referenced_image_pathsandnum_last_images_to_include. - If neither mechanism can include every target image, ask the user to attach the missing images again.
- Directly generate the image without reconfirmation or clarification unless required images must be attached again.
- After each image generation, do not mention anything related to download. Do not summarize the image. Do not ask followup question. Do not say ANYTHING after you generate an image.
- Always use this tool for image editing unless the user explicitly requests otherwise. Do not use the
pythontool for image editing unless specifically instructed.