CherryHQ-cherry-studio/.changeset/paintings-image-gen-patches.md at main

mirror of https://github.com/CherryHQ/cherry-studio.git synced 2026-07-03 12:27:41 +08:00

Files

亢奋猫 26508591f8 refactor(paintings): migrate to v2 data layer and UI (#15154 )

Co-authored-by: jidan745le <420511176@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: SuYao <sy20010504@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: fullex <106392080+0xfullex@users.noreply.github.com>
Signed-off-by: jidan745le <420511176@qq.com>
Signed-off-by: suyao <sy20010504@gmail.com>

2026-06-02 15:18:53 +08:00

806 B

Raw Permalink Blame History

@cherrystudio/ai-core, @cherrystudio/ai-sdk-provider

@cherrystudio/ai-core	@cherrystudio/ai-sdk-provider
patch	patch

Wire the v2 paintings image-generation path through patched AI SDK image models:

Activate the ai@6.0.143 patch (adds the experimental_download option to generateImage) so HTTP(S) image outputs are classified and downloaded by the SDK while data-URL outputs pass through untouched.
Extend the @ai-sdk/openai-compatible patch to support url-field image responses and skip the response_format parameter for gpt-image-* models.
Extend the @ai-sdk/google patch with model-path / isGeminiModel prefix handling for Gemini/Imagen image models.

These are targeted shims for the OpenAI-compatible / Google image gateways used by the painting providers; non-image OpenAI-compatible calls are unaffected.

806 B Raw Permalink Blame History

806 B

Raw Permalink Blame History