feat(image): pass reference images to GPT image model for edits

Server: forward canvas/reference images to the image model so extract,
continue, and edit requests stay faithful to the source product.
- Add ImageRequestOptions.Images and route requests with inputs to the
  /v1/images/edits endpoint, via multipart upload (default) or JSON
  image_url payload, selectable through Agent.Image.InputImageTransport.
- Extract reference URLs from prompt directives, inline @image tokens,
  and chat message image/mask contents; fold them into the idempotency
  key and prepend a reference-fidelity instruction to the prompt.

Frontend:
- Shrink CanvasToast to a compact top pill.
- Paste an internal transparent clipboard node instead of re-uploading
  when it matches the clipboard image.
- Keep agent-project polling alive on stream error while streaming.

This commit is contained in:

liangxu

2026-07-08 01:19:20 +08:00

parent bb7fce9171

commit 2f5291a0f9

11 changed files with 614 additions and 63 deletions

									
										server/etc/config.yaml
									
		+1
		
												View File
												
				@@ -104,6 +104,7 @@ Agent:

				    BaseURL: http://154.21.87.3:8080

				    APIKeyEnv: GPT_IMAGE_API_KEY

				    APIKey: "sk-0af1835a4e855198ec6e1ff8fb120844c146dd09b0b25b05b30ed8fa5c7be568"

				    InputImageTransport: file

				    TimeoutSeconds: 600

				ObjectStorage:

				  Driver: minio