GenarrativeAI/Genarrative
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Switch to VectorEngine gpt-image-2 and edits

Browse Source 
Replace uses of the legacy `gpt-image-2-all` model with `gpt-image-2` and standardize image workflows: no-reference generation uses POST /v1/images/generations, any-reference flows use POST /v1/images/edits with multipart `image` parts. Update SKILLs, generation scripts, decision logs, and docs to reflect the contract change and edits-vs-generations guidance. Apply corresponding changes across backend (api-server match3d/puzzle modules, openai image adapter, mappers, telemetry, spacetime client/module), frontend components and services (Match3D, Puzzle, CreativeImageInputPanel, runtime shells), and add new spritesheet/parser files and tests. Also add media/logo.png. These changes align repository code and documentation with the VectorEngine image API contract and update generation/upload handling (green-screen -> alpha processing, spritesheet handling, and related tests).
This commit is contained in:
高物
2026-05-22 03:06:41 +08:00
parent 321e1ea33a
commit ae014ac881
90 changed files with 7078 additions and 3389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
server-rs/crates/api-server/src/prompt/puzzle/draft.rs
View File

@@ -40,9 +40,11 @@ pub(crate) fn resolve_puzzle_draft_cover_prompt(
pub(crate) fn resolve_puzzle_level_image_prompt(
explicit_prompt: Option<&str>,
level_picture_description: &str,
draft_summary: &str,
) -> String {
normalize_prompt_part(explicit_prompt)
.or_else(|| normalize_prompt_part(Some(level_picture_description)))
.or_else(|| normalize_prompt_part(Some(draft_summary)))
.unwrap_or_default()
.to_string()
}
@@ -76,8 +78,15 @@ mod tests {
#[test]
fn level_image_prompt_falls_back_to_level_description() {
let prompt = resolve_puzzle_level_image_prompt(Some(" "), "关卡画面描述");
let prompt = resolve_puzzle_level_image_prompt(Some(" "), "关卡画面描述", "作品简介");
assert_eq!(prompt, "关卡画面描述");
}
#[test]
fn level_image_prompt_falls_back_to_draft_summary_like_initial_cover() {
let prompt = resolve_puzzle_level_image_prompt(Some(" "), " ", "作品简介");
assert_eq!(prompt, "作品简介");
}
}

6
server-rs/crates/api-server/src/prompt/puzzle/image.rs
View File

@@ -43,7 +43,7 @@ fn build_puzzle_image_prompt_text(_level_name: &str, prompt: &str) -> String {
concat!(
"请生成一张高清插画。",
"画面主体：{prompt}。",
"画面要求：1:1",
"画面要求：输出画面比例为1：1，",
"主体要清晰集中，前中后景层次明确，局部细节丰富但不要杂乱，",
"避免文字、水印、边框和 UI 元素。"
),
@@ -77,7 +77,7 @@ mod tests {
let prompt = build_puzzle_image_prompt("雨夜神庙", "猫咪在发光遗迹前寻找线索");
assert!(prompt.contains("猫咪在发光遗迹前寻找线索"));
assert!(prompt.contains("1:1"));
assert!(prompt.contains("输出画面比例为1：1"));
assert!(prompt.contains("主体要清晰集中"));
assert!(prompt.contains("避免文字、水印、边框和 UI 元素"));
}
@@ -90,7 +90,7 @@ mod tests {
let prompt = build_puzzle_image_prompt(long_level_name.as_str(), long_description.as_str());
assert!(prompt.chars().count() <= PUZZLE_TEXT_TO_IMAGE_PROMPT_MAX_CHARS);
assert!(prompt.contains("1:1"));
assert!(prompt.contains("输出画面比例为1：1"));
assert!(prompt.contains("主体要清晰集中"));
assert!(prompt.contains("避免文字、水印、边框和 UI 元素"));
}