Compare commits
3 Commits
ee5cec6de4
...
main
| Author | SHA1 | Date | |
|---|---|---|---|
| 12be225242 | |||
| 1b50511a4f | |||
| d6e1797f08 |
@@ -4,6 +4,134 @@
|
|||||||
|
|
||||||
## 记录
|
## 记录
|
||||||
|
|
||||||
|
### [CL-20260420-2237] 2026-04-20 22:37 — 前端一次性铺开文档中心 / 3D / 动作三大功能 UI（占位实现 + Phase 2 徽章）
|
||||||
|
- **tags**: 前端, UI, 文档中心, 3D, 动作序列, 命令面板, 工作台, 资源库, 占位实现, Phase 2, react-markdown, model-viewer
|
||||||
|
- **affected_files**:
|
||||||
|
- art-agent/frontend/package.json（新增 `react-markdown@9` / `remark-gfm@4`）
|
||||||
|
- art-agent/frontend/src/lib/types.ts（扩展 DocNode / DocTabState / View3D / Asset3D / AssetMotion / TaskType / Params3D / ParamsMotion）
|
||||||
|
- art-agent/frontend/src/lib/placeholder-store.ts（新增 docs/assets3D/assetsMotion 的 load/save/upsert/delete + 样本数据 SAMPLE_DOC_*）
|
||||||
|
- art-agent/frontend/src/lib/app-context.tsx（加入 docs/assets3D/assetsMotion/sessionTaskType/commandPaletteOpen 状态与 mutation 回调）
|
||||||
|
- art-agent/frontend/src/app/layout.tsx（挂载 `<CommandPalette />` 全局；`<model-viewer>` 用 `next/script` lazyOnload 注入）
|
||||||
|
- art-agent/frontend/src/components/layout/top-nav.tsx（在「工作台」后插入「文档」Tab，带 Phase 1 徽章）
|
||||||
|
- art-agent/frontend/src/app/docs/page.tsx（新增文档中心三栏页面：DocTree + DocTabs + DocEditor + DocOutline）
|
||||||
|
- art-agent/frontend/src/components/docs/doc-tree.tsx / doc-tabs.tsx / doc-editor.tsx / doc-outline.tsx / markdown-content.tsx / asset-picker.tsx / command-palette.tsx（新建）
|
||||||
|
- art-agent/frontend/src/components/chat/task-type-tabs.tsx（新增 2D/3D/动作任务类型切换 Tab）
|
||||||
|
- art-agent/frontend/src/components/workbench/params-3d.tsx / params-motion.tsx（新增 3D / 动作参数条，占位）
|
||||||
|
- art-agent/frontend/src/app/page.tsx（工作台注入 TaskTypeTabs + 按类型条件渲染 Params3D / ParamsMotionBar）
|
||||||
|
- art-agent/frontend/src/components/chat/task-card.tsx（新增 variant 属性：image2d/model3d/motion，颜色/图标/专有字段全套切换）
|
||||||
|
- art-agent/frontend/src/components/detail/model-3d-panel.tsx（新增：多视图/360°占位/<model-viewer> 三模式 + 通道切换 + 视图缩略条；360° 旋转用 framer-motion `rotateY` + SVG 替代 styled-jsx 避免多行 className 编译错误）
|
||||||
|
- art-agent/frontend/src/components/detail/motion-panel.tsx（新增：视频/帧序列双模式 + 播放 scrubber + MP4/GIF/帧序列占位下载）
|
||||||
|
- art-agent/frontend/src/app/gallery/page.tsx（资源库顶部加模态 Tab「图片/3D 模型/动作序列」+ Assets3DGrid / AssetsMotionGrid 两个子组件；3D/MOTION 徽章和视角/帧数徽章叠加显示；接 detail 面板）
|
||||||
|
- art-agent/frontend/src/components/ui/motion-presets.ts（`sendBounce` 的 `ease: "easeInOut"` 加 `as const`，修预存 framer-motion 类型错误不阻塞 build）
|
||||||
|
- **what**:
|
||||||
|
按用户一次性铺开「文档管理中心（类似 Cursor）/ 3D 模型生成 / 动作生成」全部界面元素与交互的要求，用占位实现把所有入口、组件、面板、参数条、徽章与跳转都先打通：
|
||||||
|
1. 文档中心：`/docs` 三栏布局（树/Tab+编辑器/大纲），支持 Markdown textarea 编辑 + react-markdown 预览 + 分屏、`[[asset:id]]` 资产引用（图片/角色/风格）在正文内渲染为交互卡片、拖拽/重命名/新建/删除、AssetPicker 浮层。
|
||||||
|
2. 命令面板：Cmd/Ctrl+K 全站 CommandPalette，整合导航/动作/文档/图片/角色/风格/会话的统一搜索。
|
||||||
|
3. 工作台扩展：任务类型 Tab（2D/3D/动作），按类型显示不同参数条（`Params3D` 含管道/视图数/分辨率，`ParamsMotionBar` 含模型/帧数/帧率/循环/输出/角色绑定/动作描述）；`TaskCard` 加 `variant` 区分颜色/图标/描述/专有字段（3D 显示管道+视图数+产物，动作显示帧数+循环+产物）。
|
||||||
|
4. 结果详情：`Model3DPanel` 支持多视图切换（color/normal/stylized 三通道 + 视图缩略条）/ 360°占位旋转 / `<model-viewer>` 模型预览三模式；`MotionPanel` 支持视频/帧序列双模式 + 播放 scrubber。
|
||||||
|
5. 资源库：顶部新增模态 Tab（图片/3D 模型/动作序列）+ 计数徽章 + Phase 徽章；3D 网格叠 `3D` 徽章+视角数，动作网格叠 `MOTION` 徽章+帧数·fps + hover 自动播放视频。
|
||||||
|
- **why**:
|
||||||
|
用户明确要求"所有功能都先用占位把界面元素和交互实现出来，避免后续反复返工"。选择"一次性完整铺开"策略而非渐进式，可让用户在真实管线（Mesh Pipeline / 动作生成后端）接入前就能验收完整 UX 流与设计语言一致性，减少后端开发时 UI 的认知负担。
|
||||||
|
- **decisions**:
|
||||||
|
- 选 **react-markdown + remark-gfm** 轻量 textarea 方案（否决 Monaco/TipTap：文档场景还不需要代码折叠/语法高亮/WYSIWYG，先保持依赖干净）。
|
||||||
|
- **站内 Cmd+K 命令面板**统一搜索（否决每页独立搜索：符合 Cursor 风格且跨域跳转一致）。
|
||||||
|
- 3D 预览走 **`<model-viewer>` 自定义元素**（否决 three.js/react-three-fiber：占位阶段用现成自定义元素最省代码，真实接入时只需把 `asset.meshUrl` 换成真实 GLB 路径；用 `next/script` lazyOnload 避免阻塞首屏）。
|
||||||
|
- 动作预览走 **HTML5 `<video>`**（否决 GIF：mp4 文件更小 + 支持帧擦写；GIF 只作下载选项保留）。
|
||||||
|
- 「文档」Tab 放 **TopNav 第 2 位**（「工作台」之后），符合用户对"近 workspace"的访问距离预期。
|
||||||
|
- Model3D 面板的 360°预览**放弃 styled-jsx CSS 立方体**（6 face 的 styled-jsx 触发 webpack 对多行 className 的解析错误），改用 framer-motion `rotateY` 驱动 SVG 六边形，更简洁且不会和 webpack 打架。
|
||||||
|
- **notes**:
|
||||||
|
1. 所有新组件均标 `phase-chip`（文档 Phase 1 / 3D·动作 Phase 2），真实链路接入时只需替换 placeholder-store 的 loader 和 `upsert*` 的写入方向。
|
||||||
|
2. `<model-viewer>` 脚本是从 unpkg lazyOnload 加载，生产环境若断网/被墙 3D 模式会静默降级（只显示占位文案），可在 Phase 2 接入时改为本地打包。
|
||||||
|
3. `chat-input.tsx` 的 framer-motion 类型错误（`ease: string` 不匹配新版 `Easing` 联合类型）顺手在 `motion-presets.ts` 源头用 `as const` 修掉，`npx next build` 已通过全绿。
|
||||||
|
4. TopNav 的「文档」Tab 是全站入口，新建文档/打开文档走 Ctrl/Cmd+K 也能到，两者使用同一份 `docs` 状态。
|
||||||
|
5. 资源库的 3D / 动作模态下不显示「收藏/标签/视图切换」等图片专属工具栏（条件分支上移到 `<main>` 内部），避免误导用户这些控件对 3D/动作生效。
|
||||||
|
- **source_chat**: [前端铺开三大功能占位 UI](4f55b11a-3572-47e2-8292-7d815773e7ad)
|
||||||
|
|
||||||
|
### [CL-20260420-1800] 2026-04-20 18:00 — Mesh Pipeline Phase 3 风格还原接入（IP-Adapter + ControlNet）
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, 风格还原, IP-Adapter, ControlNet, Replicate, style_restorer, 后端, services, config, Phase 3
|
||||||
|
- **affected_files**:
|
||||||
|
- art-agent/backend/app/config.py
|
||||||
|
- art-agent/backend/app/services/style_restorer.py (新增)
|
||||||
|
- art-agent/backend/app/services/view_transform.py
|
||||||
|
- art-agent/backend/scripts/test_style_restore.py (新增)
|
||||||
|
- docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **what**: 按 SPEC §4 Phase 3 落地 Mesh Pipeline 的阶段 3 — 对 Stage 2 抽出的 normal 帧做 IP-Adapter + ControlNet 重绘，用用户原图做风格参考，输出保留原画风且视角正确的最终图。
|
||||||
|
- **why**: Phase 2 已能稳定产出 color/normal 6 视角帧，但 Trellis 的 color 帧是"半写实"纹理风，与用户上传的卡通描边原图风格差异明显。Phase 3 用 `chigozienri/ip_adapter-sdxl-controlnet-depth`（版本 `0436c870...`，$0.07/张 ~72s，L40S）：`image` 字段传原图承担 IP-Adapter 风格参考，`controlnet_input` 传 normal 帧作为结构约束的 depth 近似（按 SPEC §1.4 一期走"路 A"简化方案，效果不足再升级为 `depth-anything-v2` 真 depth）。
|
||||||
|
- **decisions**:
|
||||||
|
1. 新模型以 `internal=True` 注册进 `IMAGE_MODELS`（而非 `VIEW_TRANSFORM_MODELS`），理由：它是"普通文生/图生图"模型，只是用在内部流水线；同步改 `get_image_models_list()` 过滤 `internal`，避免它出现在前端生图模型下拉
|
||||||
|
2. 暴露 `get_style_restore_model_id()` helper 让 service 层不硬编码短 ID
|
||||||
|
3. `restore_batch()` 用 `asyncio.Semaphore(3)` 控制并发而非 `asyncio.gather` 全冲 —— SPEC §5 风险表提示过 Replicate rate limit 风险
|
||||||
|
4. 默认参数选 `scale=0.75` / `controlnet_conditioning_scale=0.8`（SPEC §2.3 建议范围 0.7-0.8 / 0.7-0.9 的中位偏上），最终值由 P3-4 调参确认
|
||||||
|
5. **单帧失败不阻塞整体**：Stage 3 任一帧失败时自动回退为 Stage 2 的 color 帧返回，前端至少能看到东西；并在该 image 上挂 `restyle_error` 字段暴露失败原因。这一兜底 + "Stage 2 失败不影响 Stage 1 交付" 形成一致的"阶段独立可交付"设计
|
||||||
|
- **notes**:
|
||||||
|
- 成本：一次完整 6 视角请求 ~$0.46（Trellis $0.041 + 6 × IP-Adapter $0.07 = $0.461），耗时 ~105s（30s 重建 + 并发 3 两轮 × 72s ≈ 75s 风格化）
|
||||||
|
- `images[i]` 新结构：新增 `color_url`（保留 Stage 2 原图便于前端对比/切换）、`restyled` 布尔、可选 `restyle_error`；返回体 `_stage` 从 `stage2` 升级为 `stage3 (N/M restyled)`
|
||||||
|
- `_note` 字段去掉了，错误通过 `error` 字段聚合（拼接 Stage 2 + Stage 3 错误）；`_preserve_style_requested` 保留供调试
|
||||||
|
- Checkpoint 3 脚本 `scripts/test_style_restore.py` 支持 `--single` 冒烟（~$0.07）和全量（~$0.42），以及 `--scale/--cn-scale` 临时覆盖参数，便于 P3-4 调参；默认自动挑 generated/ 下最新一组 `view_<prefix>_az*_el0_normal.png` 作为结构参考
|
||||||
|
- **P3-4 未完成**（等用户用真实原图跑调参）；P4 前端联调将在 Checkpoint 3 通过后开启
|
||||||
|
- **source_chat**: [继续执行 Mesh Pipeline Phase 3](85c3e2f0-ab1f-48c3-9f12-a1b2c3d4e5f6)
|
||||||
|
|
||||||
|
### [CL-20260420-1700] 2026-04-20 17:00 — Mesh Pipeline Phase 2 抽帧 + combined_video 左右切分落地
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, Trellis, combined_video, ffmpeg, imageio-ffmpeg, PIL, 抽帧, 后端, services, Phase 2
|
||||||
|
- **affected_files**:
|
||||||
|
- art-agent/backend/app/services/video_frame_extractor.py (新增)
|
||||||
|
- art-agent/backend/app/services/view_transform.py
|
||||||
|
- art-agent/backend/requirements.txt
|
||||||
|
- art-agent/backend/scripts/test_frame_extract.py (新增)
|
||||||
|
- docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **what**: 按 SPEC §4 Phase 2 清单落地。(1) 确认宿主机 `ffmpeg` 未安装，改用 `imageio-ffmpeg==0.5.1` 自带的 Windows 静态二进制（`ffmpeg-win64-v4.2.2.exe`，随 wheel 一起打包 22.6MB），免系统依赖；venv 已装，`requirements.txt` 同步写入。(2) 新增 `services/video_frame_extractor.py` 实现 `extract_by_azimuth(combined_video_path, azimuths, elevations=None, total_rotation_deg=360)`：核心策略采用"一次性把 combined_video 所有帧抽到 `generated/_frames_<id>/` 临时目录 + 按 `frame_idx = round(az / total_rotation_deg * total_frames) % total_frames` 挑帧 + PIL 按中线切左半→color、右半→normal 保存到 `generated/view_<batch>_az{az}_el{el}_{color|normal}.png`"，比逐帧用 `-ss` 抽更稳（不受 keyframe 对齐影响），5s 视频整体成本可忽略；用完即清理临时目录，只保留切好的最终帧。(3) ffmpeg + PIL 是阻塞操作，用 `asyncio.get_running_loop().run_in_executor(None, _do_extract, ...)` 丢到默认线程池跑，避免堵住 FastAPI 事件循环。(4) `services/view_transform.py`：`_transform_view_mesh` 在 Stage 1 成功后串接 Stage 2——默认 `azimuths=[0,60,120,180,240,300]`（从模块级常量 `DEFAULT_MESH_AZIMUTHS` 读取），`elevations` 缺省或长度不足补 0、超长截断，保证与 azimuths 对齐；调用 `video_frame_extractor.extract_by_azimuth(combined_video_path=stage1["combined_video_path"], ...)` 得到 `frames[{az, el, frame_idx, color_png, normal_png}]`；把 `images` 填为 `[{url: color_png, azimuth, elevation, normal_url: normal_png, frame_idx}]`；Stage 2 失败**不**把整体置为失败（Stage 1 的 mesh/video 仍有交付价值），单独在返回 dict 的 `error` 字段带回 Stage 2 错误信息，`success` 同时要求 stage1 成功 + Stage 2 无 error。(5) 新增 `scripts/test_frame_extract.py` 供用户 Checkpoint 2 验收：默认取 `generated/` 下最新的 `trellis_combined_*.mp4` 做输入（**不需要再花钱跑 Trellis**），调用 `video_frame_extractor.extract_by_azimuth` 抽 6 视角，打印每帧的 `color_png/normal_png` URL + 本地文件大小，并提示用户目视检查。(6) SPEC 文档 P2-1 ~ P2-4 全部打勾、追加本次会话的进度 note（含 Agent 自测结论）。
|
||||||
|
- **why**: SPEC §4 "每个 Phase 完成后停下来让用户测试/审阅"，Phase 2 是用户能看到"可见结果"的第一步——Phase 1 只能交付一个 .glb + 一个 mp4 视频，用户很难一眼判断是否正确；Phase 2 交付 6 张方位角明确的方形图后，用户可以直接目视环绕教堂一周。抽帧方案故意选"一次抽全 + 按索引挑"而不是"每帧一次 -ss 快进"，是因为：(a) combined_video 约 5s/120 帧，总 PIL+ffmpeg 开销 ~1-2s，比 6 次 -ss (每次 ffmpeg 启动 ~300-500ms) 更快；(b) `-ss` 在 GOP 长的 mp4 上会对齐到最近 keyframe，取帧索引可能不精确；(c) 代码简单、debug 时看临时目录文件序号就能对应帧。Stage 2 失败不牵连 Stage 1，是考虑到"抽帧失败"通常意味着 ffmpeg 或视频本身异常，但用户可能仍想拿 .glb 做手动检视——与其整体 fail，不如降级返回部分产物 + 明确 error。测试脚本用已有 combined_video 是故意为之：Checkpoint 2 的重点是验证抽帧+切图的正确性，不是再验证一遍 Trellis，没理由让用户多花 $0.041。
|
||||||
|
- **decisions**: (1) **ffmpeg 方案**：首选 `imageio-ffmpeg` 而不是让用户 `choco install ffmpeg`，因为 SPEC §5 风险栏就列了 "Windows ffmpeg 未装" 是高概率风险，imageio-ffmpeg 的 pip wheel 自带 Win64 二进制是零摩擦方案；代价是 wheel 22.6MB + 每次 Python 启动查找二进制（成本可忽略）。(2) **返回 schema**：给 mesh 管道的 `images[i]` 加了 `normal_url` 和 `frame_idx` 字段而不是单独的 `frames` 列表——这样前端不用改 schema 就能显示（`url` 仍是最终要展示的彩色图），同时 Phase 3 可以直接读 `normal_url` 作为 `controlnet_input`。(3) **elevation 字段保留但忽略**：combined_video 本身是水平平视一圈，`elevation != 0` 在 Phase 2 无意义（所有帧 el 都是 0），但保留字段为 Phase 5 自由相机路径预留；当前传 `elevations=[30,30,...]` 也不会报错，只是结果图的 el 字段被原样记录、帧内容仍是水平视角（有心理预期即可，未来 renderer 路径会真正使用）。(4) **临时目录策略**：抽帧到 `generated/_frames_<8位hex>/` 而不是系统临时目录，是因为后者在 Windows 跨盘符时可能慢；前者失败时也留现场方便 debug。完成后的清理用 `try/except OSError` 兜底，即使 PIL 占着句柄也不会报错退出。(5) **DEFAULT_MESH_AZIMUTHS 提到模块级**：下 Phase 4 前端会暴露"快速预设 6/8/12 视角"选项，这里先把默认值拎出来便于配置扩展；目前命名为 6 视角，Phase 4 再考虑增加 8/12。
|
||||||
|
- **notes**: (1) **Stage 2 路径依赖 stage1 的 `combined_video_path` 键名**（非 `color_video_path`）——这是 Trellis 部署版 `e8f6c452...` 的实测事实（PF-20260420-1600），不要以为 Phase 1 的字段 `color_video_path` 有值；现在该字段仍然返回但恒为 `None`，`_transform_view_mesh` 里优先读 `combined_video_path`。(2) **前端目前仍不会自动展示 mesh 管道结果** ——`loop.py` 只在 `result.get("images")` 非空时发 `image_result` 事件，Phase 2 让 images 有值了，所以前端**应该**能看到 6 张；但 Phase 4 才正式端到端联调，Phase 2 的建议验收入口仍是 `scripts/test_frame_extract.py` 而不是 UI。(3) **normal 帧的 url 在前端目前是"隐藏字段"**——`images[i].normal_url` 前端 types.ts 里没这个字段，会被丢弃；Phase 3 接入时 view_transform 会改为把重绘后的图填到 `url`，normal 帧继续作为中间产物留在磁盘上。(4) **预留的 `preserve_style` 参数当前不生效**，返回 dict 的 `_preserve_style_requested` 字段记录了用户意图——Phase 3 会根据这个开关分流（True 走 ControlNet 重绘、False 直出 color 帧）。(5) **Agent 自测结果（2026-04-20 17:05）**：`test_frame_extract.py` 对 `trellis_combined_290da12de954.mp4` 运行，抽出 120 帧，az=[0,60,120,180,240,300] 分别映射到 frame_idx=[0,20,40,60,80,100]（每 60° = 20 帧）完全均匀，12 个 PNG 全部落盘，单张尺寸 512×512 方形（说明原 combined_video 是 1024×512 左右并排）。自测**不能替代用户目视检查** "6 张 color 图是否按 0°→300° 顺序环绕建筑一圈"，Checkpoint 2 必须由用户拍板。(6) 用户验收流程：(a) 在 `art-agent/backend` 激活 venv；(b) 跑 `python scripts/test_frame_extract.py`（默认取 `generated/` 最新 trellis_combined；也可 `python scripts/test_frame_extract.py generated/trellis_combined_<hash>.mp4` 指定）；(c) 终端应打印 6 个 color_png + 6 个 normal_png 均 `OK`，每个 size > 0；(d) 打开 `generated/view_*_az0_el0_color.png ~ view_*_az300_el0_color.png` 6 张图，验证是同一建筑从 6 个均匀角度绕一圈的视角；(e) normal 图是蓝紫调法线图，可抽 1-2 张抽查。通过后开 Phase 3。
|
||||||
|
- **source_chat**: 本次会话 "继续执行 Phase 2"
|
||||||
|
|
||||||
|
### [CL-20260420-1600] 2026-04-20 16:00 — Mesh Pipeline Phase 1 接入 Trellis（视角变换第二条管道落地阶段 1）
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, Trellis, Replicate, 后端, services, config, tools, Phase 1
|
||||||
|
- **affected_files**:
|
||||||
|
- art-agent/backend/app/services/mesh_generator.py (新增)
|
||||||
|
- art-agent/backend/app/services/view_transform.py
|
||||||
|
- art-agent/backend/app/config.py
|
||||||
|
- art-agent/backend/app/agent/tools.py
|
||||||
|
- art-agent/backend/scripts/test_trellis.py (新增)
|
||||||
|
- docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **what**: 按 SPEC §4 Phase 1 清单落地。(1) 新增 `services/mesh_generator.py`，封装 `generate_with_trellis(image_path, params=None)` 和统一入口 `generate_mesh(image_path, model_id)`，调用 `firtoz/trellis:e8f6c452...` 并把 `model_file/color_video/normal_video/combined_video` 挨个 httpx 下载到 `GENERATED_DIR`，以 `trellis_*_<uuid>.{glb,mp4}` 命名，返回 `/generated/...` 本地 URL。(2) `config.py` 在 `VIEW_TRANSFORM_MODELS` 新增 `trellis`（pipeline=mesh, enabled=True）和 `hunyuan3d`（pipeline=mesh, enabled=False 占位），给原 `zero123plus` 条目补 `pipeline=grid`；`get_view_transform_models_list` 改为只返回 enabled 条目 + 带上 pipeline 字段。(3) `services/view_transform.py` 改为按 `pipeline` 字段分流——`grid` 走原 Zero123++ 逻辑（逻辑未动，仅输出字段补齐 `pipeline/mesh_url/color_video/normal_video`），`mesh` 走新增 `_transform_view_mesh()`：当前阶段只跑 mesh_generator 返回 `.glb + color_video + normal_video` 本地 URL，`images` 列表留空，附 `_stage="stage1"` 和 `_note` 标记 Phase 2/3 未接入。(4) `tools.py` 的 `transform_view` 工具定义扩三个参数 `model_id` (enum: zero123plus/trellis, default zero123plus) / `azimuths` / `preserve_style`，执行侧把这些参数透传给 `transform_view()`。(5) 新增 `backend/scripts/test_trellis.py` 作为 Phase 1 独立验收脚本——默认用 uploads/ 下最新 png、支持命令行指定路径、自动加载 .env、调用 `mesh_generator.generate_with_trellis` 后检查本地文件大小。(6) SPEC 文档 P1-1 ~ P1-5 打勾并追加进度 note。
|
||||||
|
- **why**: SPEC 明确要求"按 Phase 顺序推进，每个 Phase 完成后停下来让用户测试/审阅"，Phase 1 是整条 Mesh Pipeline 的地基——验证 Replicate Trellis 调用通道是否打通、文件下载策略是否正确、与现有 grid 管道并存不互相干扰。把 mesh_generator 独立成模块是为后续 Phase 2/3/5 解耦：Phase 2 只需读 color_video_path/normal_video_path，Phase 3 只需消费 images 列表，Phase 5 切到 Hunyuan3D-2 时只需替换 generate_mesh 的分支。测试脚本独立走 asyncio 是因为 Phase 1 还没接到工具链，用户需要一个"最小能跑"的入口先确认 API 本身可用（SPEC P1-5 也是这么要求的）。
|
||||||
|
- **decisions**: (1) `view_transform` 返回结构升级为同时带 `grid_image/mesh_url/color_video/normal_video/pipeline` 字段，两种管道缺省位补 `None`——比"两种完全不同的返回 schema"更利于前端和 loop.py 后续统一处理。(2) Phase 1 当前故意让 mesh 管道的 `images` 为空 + 带 `_note` 说明，而不是硬拼一个"只返回视频"的假结果——这样 Phase 2 接入时 frontend 的 "没有图片显示" 现象会被替换为 "6 张图片显示"，语义更清晰。(3) hunyuan3d 提前注册但 `enabled=False`，避免用户在前端误选到二期才启用的路径；`get_view_transform_models_list` 同步过滤 enabled。(4) `mesh_generator._to_url` 做了 `FileOutput → str` 的显式转换兜底，因为 Replicate SDK 的字典输出里每个字段可能是 FileOutput 对象而不是裸字符串 URL——这点在 image_gen.py 的 `ReplicateProvider._download` 已经吃过亏，这里主动规避。(5) `_download_asset` 的 httpx 超时放到 300s，因为 color_video ~3-5MB 在国内网络可能慢；复用项目既有的 HTTPS_PROXY 注入模式。
|
||||||
|
- **notes**: 本次改动**完全不触碰 Zero123++ 现有流程**——grid 管道所有行为保持 byte-level 等价，只是返回字典多了几个 None 字段，`loop.py` 和前端已有代码没事。但还**未修改 loop.py 的 SSE 事件处理**：当前 loop.py 只在 `tool_name == "transform_view" and result.get("images")` 时发 `image_result`；mesh 管道 Phase 1 的 `images=[]` 会让 loop.py 不发事件，前端看到空结果——这**是预期行为**，Phase 1 的测试入口是 `scripts/test_trellis.py` 而不是前端。Phase 2 接入后 images 有值，loop.py 无需改动即可工作。用户验收流程：(a) 在 `art-agent/backend` 激活 venv；(b) 跑 `python scripts/test_trellis.py`（默认取 uploads/ 最新 png），或 `python scripts/test_trellis.py uploads/<hash>.png` 指定图；(c) 等 ~30-60s 看终端打印 `glb_path/color_video_path/normal_video_path` 均为 `/generated/trellis_*...` + 本地大小 > 0；(d) 可选：去 `backend/generated/` 目录用系统播放器看 color_video.mp4 是否为 360° 环绕教堂视频。验收通过后我再开 Phase 2（ffmpeg 抽帧）。
|
||||||
|
- **source_chat**: 本次会话 "按计划实施 Mesh Pipeline"
|
||||||
|
|
||||||
|
### [CL-20260420-1530] 2026-04-20 15:30 — 写入 Mesh-Pipeline 视角变换方案 SPEC（跨会话实施计划）
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, Trellis, Hunyuan3D-2, ControlNet, IP-Adapter, SPEC, 方案设计, 建筑, 跨会话
|
||||||
|
- **affected_files**:
|
||||||
|
- docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **what**: 新增一份完整的实施计划 SPEC，规划 Zero123++ 之外的第二条视角变换路径——Mesh Pipeline。三段式流水线：(1) Trellis/Hunyuan3D-2 单图生 mesh + 360° color_video；(2) ffmpeg 从 color_video 抽指定 azimuth 的帧（一期方案，免 pyrender）；(3) `chigozienri/ip_adapter-sdxl-controlnet-depth` 做 SDXL+ControlNet-Depth+IP-Adapter 二次重绘，用原图保持卡通描边风格。文档含：三个 Replicate 模型的精确版本 ID + OpenAPI schema、config.py 扩展设计、伪代码管道、6 个 Phase 的可独立执行任务清单（每个 Phase 有独立验收标准）、风险兜底、成本预估（~$0.46/~105s）、跨会话恢复指引。
|
||||||
|
- **why**: 用户反馈 Zero123++ 只能出 6 个固定视角 + 建筑大角度偏转一致性差。用户选定重流水线（P1-P3 全做），明确要求"保留 2D 卡通风格"+"自包含跨会话执行"。调研中发现：Trellis ($0.041/30s 自带 color_video) 比 Hunyuan3D-2 ($0.12/127s 仅 mesh) 快 4× 便宜 3×，一期走 Trellis 还能省掉自定义渲染模块。把 Hunyuan3D-2 路线拆进 Phase 5（二期可选），工程量从 ~9h 降到 ~5h。
|
||||||
|
- **decisions**: 主选 Trellis 而非 Hunyuan3D-2——以便一期完全跳过 pyrender/blender 渲染器（用 ffmpeg 抽帧替代）。阶段 3 的 ControlNet 结构约束用 normal_video 抽帧（Trellis 送的），不先走 depth-anything-v2（省一次 API 调用，不完美但足够）。Hunyuan3D-2 + pyrender 自由相机留作 Phase 5 可选。不在一期解决 elevation 仰俯视角（Trellis color_video 只给水平环绕），那是 Phase 5 的事。
|
||||||
|
- **notes**: 文档位置 `docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md`。下一个会话开工时 Agent 需先读 §0-§3 建立背景，再按 §4 Phase 顺序推进，每 Phase 交付后停下来让用户验证。文档底部有"进度日志"章节，每个 Phase 完成后在 checkbox 打勾 + 追加 note。未修改任何业务代码，纯 SPEC 文档。
|
||||||
|
- **source_chat**: 本次会话排查 Zero123++ 切图错位 meta-bug + 后续方案调研
|
||||||
|
|
||||||
|
### [CL-20260420-1501] 2026-04-20 15:01 — 后端增加 watchfiles 依赖，修复 Windows uvicorn --reload 失效
|
||||||
|
- **tags**: uvicorn, watchfiles, 热重载, Windows, FastAPI, requirements, 依赖管理, reload, Zero123++
|
||||||
|
- **affected_files**:
|
||||||
|
- art-agent/backend/requirements.txt
|
||||||
|
- art-agent/backend/requirements-lock.txt
|
||||||
|
- **what**: 在 `requirements.txt` 和 `requirements-lock.txt` 中显式加入 `watchfiles==0.24.0`，并在当前 venv 中安装。这让 uvicorn `--reload` 使用 WatchFiles 作为 reloader 后端，而不是无依赖时的 StatReload 轮询回退。
|
||||||
|
- **why**: 用户反馈 Zero123++ 切图错位——但 CL-20260420-1212 里做的 `cols=2/rows=3` 修复和 `_split_grid_image` 自动纠错逻辑在磁盘上明明是新版，独立调用也能切出正确的 320×320。进一步排查发现后端 uvicorn 进程是 11:55 启动、从未 reload，而 venv 里 `watchfiles`/`watchdog` 均未安装——StatReload 在 Windows + 深层子目录 + 新建文件 (`view_transform.py` 是 untracked 新增) 的叠加场景下几乎完全失效，所以代码改了但运行时还是老版本。这一层 meta-bug 如果不治本，以后每次改后端都要手动重启。
|
||||||
|
- **decisions**: 选择 `watchfiles`（uvicorn 官方推荐、跨平台 Rust 实现、依赖最轻）而不是 `watchdog`（历史包袱更重）。版本锁 0.24.0 与 Python 3.12 兼容良好且 uvicorn 0.44.0 默认识别。未添加 `--reload-dir app` 参数到 project-launcher Skill 的启动命令里——先靠装依赖覆盖主要场景，如果未来仍有监听遗漏再显式限定目录。
|
||||||
|
- **notes**: **仅装依赖不重启当前 uvicorn 进程不会生效**，因为旧进程已经绑定到 StatReload。需要 kill PID 28172 并重启一次后端，之后所有代码改动才会自动 reload。启动日志里应该能看到 `Started reloader process [xxx] using WatchFiles`，如果仍是 `StatReload` 说明 watchfiles 没正确安装到当前 venv。踩坑已记录 PF-20260420-1501。
|
||||||
|
- **source_chat**: 本次会话排查 Zero123++ 切图错位 meta-bug
|
||||||
|
|
||||||
|
### [CL-20260420-1212] 2026-04-20 12:12 — 修复 Zero123++ 视角切图布局反转导致的图像错位
|
||||||
|
- **tags**: Zero123++, 视角变换, 切图, bug修复, grid_layout, PIL, Replicate, view_transform
|
||||||
|
- **affected_files**:
|
||||||
|
- art-agent/backend/app/config.py
|
||||||
|
- art-agent/backend/app/services/view_transform.py
|
||||||
|
- **what**: 修复 `transform_view` 输出的 6 张视角图严重错位的问题。`config.py` 里的 `VIEW_TRANSFORM_MODELS["zero123plus"].grid_layout` 由 `{"cols": 3, "rows": 2}` 改为 `{"cols": 2, "rows": 3}`，与 `jd7h/zero123plusplus` Replicate 实际输出（高图布局）一致。同时在 `view_transform._split_grid_image` 加入"按实际图像长宽比自动纠正 cols/rows"的健壮性保护：假定每个单视角为正方形，若配置的 `cols/rows` 与图像实际 `w/h` 差异超过 20%，自动交换 cols/rows 并记录 warning。
|
||||||
|
- **why**: 用户反馈视角变换后的切图全部错位（窄长条、上下拼两个物体）。根因是 Zero123++ 官方 README 写 "3×2 grid" 但实际 Replicate 部署版输出的是 2 列 × 3 行（高图），config 里按"3 列 × 2 行"配置，cell_w/cell_h 算反了。加上动态纠错是为了未来换其他 view transform 模型时不再重复踩这个坑。
|
||||||
|
- **decisions**: 选择"修 config + 加运行时自动纠错"而非仅修 config。纯改 config 能解决眼前问题但无法防御未来模型切换；加动态纠错的代价只是一段 if 判断+warning 日志，换取对"布局文档歧义"场景的整体免疫。放弃了更激进的"用 PIL 探测内容块边界"方案，因为对有微量白边/噪声的模型不稳定。
|
||||||
|
- **notes**: uvicorn 以 `--reload` 方式运行，改完自动重载，无需重启服务。用户需要在前端重新触发一次视角变换来验证切图是否正确。对应踩坑记录已写入 `.cursor/pitfalls/pitfalls.md` (PF-20260420-1212)。
|
||||||
|
- **source_chat**: 本次会话启动项目并调试 Zero123++ 切图
|
||||||
|
|
||||||
### [CL-20260417-1510] 2026-04-17 15:10 — Cloudflare Quick Tunnel 脚本修复（PS5.1 编码 + 本地 cloudflared）
|
### [CL-20260417-1510] 2026-04-17 15:10 — Cloudflare Quick Tunnel 脚本修复（PS5.1 编码 + 本地 cloudflared）
|
||||||
- **tags**: 内网穿透, cloudflared, PowerShell, start-tunnel, UTF-8, gitignore
|
- **tags**: 内网穿透, cloudflared, PowerShell, start-tunnel, UTF-8, gitignore
|
||||||
- **affected_files**:
|
- **affected_files**:
|
||||||
|
|||||||
@@ -2,6 +2,13 @@
|
|||||||
|
|
||||||
最近 ~50 次改动的一句话概要，按时间倒序排列。每次会话自动注入上下文。
|
最近 ~50 次改动的一句话概要，按时间倒序排列。每次会话自动注入上下文。
|
||||||
|
|
||||||
|
- [CL-20260420-2237] 前端一次性铺开文档中心（/docs 三栏 + DocTree/Tabs/Editor/Outline + react-markdown + `[[asset:id]]` 资产引用 + AssetPicker）+ 全站 Cmd/Ctrl+K CommandPalette + 工作台 TaskTypeTabs（2D/3D/动作）按类型显示 Params3D/ParamsMotionBar + TaskCard 加 variant + 3D 结果面板 Model3DPanel（多视图/360°/`<model-viewer>` 三模式，color/normal/stylized 通道切）+ 动作结果面板 MotionPanel（视频/帧序列双模式+scrubber）+ 资源库顶部模态 Tab（图片/3D/动作）+ 3D/MOTION 徽章叠加；`<model-viewer>` 走 next/script lazyOnload；types/placeholder-store/app-context 全量扩展 doc/assets3D/assetsMotion；顺手把 `sendBounce` 的 `ease` 加 `as const` 修预存 build 类型错，`npx next build` 全绿
|
||||||
|
- [CL-20260420-1800] 按SPEC §4 Phase 3落地Mesh Pipeline风格还原：config注册internal=True的ip-adapter-controlnet-depth（$0.07/张）+ get_image_models_list过滤internal；新增services/style_restorer.py(restore/restore_batch带Semaphore并发3防rate limit)；view_transform._transform_view_mesh接入Stage 3，preserve_style=True时用原图做IP-Adapter风格参考+normal帧做ControlNet结构约束（SPEC §1.4路A），单帧失败自动回退Stage 2 color帧不阻塞整体，images[i]新增color_url/restyled/restyle_error，_stage升级为stage3 (N/M restyled)；新增scripts/test_style_restore.py支持--single冒烟/全量/--scale/--cn-scale覆盖参数复用Phase 2 normal帧免重跑Trellis；默认scale=0.75 cn_scale=0.8，P3-4调参等用户验收；一次完整6视角 ~$0.46/~105s
|
||||||
|
- [CL-20260420-1700] 按SPEC §4 Phase 2落地Mesh Pipeline阶段2：新增services/video_frame_extractor.py用imageio-ffmpeg静态二进制(系统ffmpeg未装的兜底)+PIL一次抽全帧到temp dir再按帧索引挑6个方位角+切左右半得color/normal；view_transform.py的mesh管道现已走到Stage2返回images[{url,azimuth,elevation,normal_url,frame_idx}]；Stage 2失败不牵连Stage1的mesh/video产物；新增scripts/test_frame_extract.py复用已有combined_video做验收省钱；requirements加imageio-ffmpeg==0.5.1；Agent自测120帧视频6视角映射到0/20/40/60/80/100索引+512×512切图均正确；等用户Checkpoint 2验收后开Phase 3
|
||||||
|
- [CL-20260420-1600] 按SPEC §4 Phase 1落地Mesh Pipeline阶段1：新增services/mesh_generator.py封装Trellis调用+下载.glb/color_video/normal_video到generated/，config注册trellis(enabled)+hunyuan3d(占位)+加pipeline字段，view_transform.py按pipeline分流grid/mesh，tools.py扩model_id/azimuths/preserve_style，新增scripts/test_trellis.py独立验收入口；Zero123++现有流程完全不变；等用户跑脚本验收后开Phase 2
|
||||||
|
- [CL-20260420-1530] 写入Mesh-Pipeline视角变换方案SPEC（跨会话实施计划）：Trellis生mesh+360°video→ffmpeg抽帧→IP-Adapter+ControlNet重绘保留卡通风，含3个Replicate模型版本ID/schema+6 Phase任务清单+风险兜底，位于docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- [CL-20260420-1501] 后端装watchfiles并写入requirements，修复Windows uvicorn --reload退化为StatReload导致代码改动不热重载（view_transform 12:12改完但后端15:00仍跑旧码），踩坑PF-20260420-1501；需重启后端生效
|
||||||
|
- [CL-20260420-1212] 修复Zero123++切图错位：jd7h部署版实际输出2列×3行而非3×2，config改cols=2/rows=3，_split_grid_image新增按实际ratio自动纠错（防御未来布局歧义），踩坑记为PF-20260420-1212
|
||||||
- [CL-20260417-1510] start-tunnel.ps1 修复 PS5.1 中文 here-string 解析失败：WriteAllLines 写 .env、脚本 UTF-8 BOM、同目录 cloudflared.exe 优先；根 .gitignore 忽略下载的 cloudflared.exe
|
- [CL-20260417-1510] start-tunnel.ps1 修复 PS5.1 中文 here-string 解析失败：WriteAllLines 写 .env、脚本 UTF-8 BOM、同目录 cloudflared.exe 优先；根 .gitignore 忽略下载的 cloudflared.exe
|
||||||
- [CL-20260417-1500] 按 INFOLAYER.md 一次性铺开 Phase 1+ 前端 UI 骨架：新增风格库/角色库/训练中心/项目设置四大页面模块+工作台快选条+高级控制+候选评估+Task Card+资源库多维过滤，placeholder-store.ts 管理占位数据，phase-chip 标注阶段
|
- [CL-20260417-1500] 按 INFOLAYER.md 一次性铺开 Phase 1+ 前端 UI 骨架：新增风格库/角色库/训练中心/项目设置四大页面模块+工作台快选条+高级控制+候选评估+Task Card+资源库多维过滤，placeholder-store.ts 管理占位数据，phase-chip 标注阶段
|
||||||
- [CL-20260416-1600] 视觉风格从暗绿底全面转为白底青绿（绢本山水）：背景#FAFAF7+文字#1A1A1A+accent#2E8B7A，13个文件颜色替换，面板改白色毛玻璃，云雾透明度降低，VISUAL-STYLE-GUIDE.md重写
|
- [CL-20260416-1600] 视觉风格从暗绿底全面转为白底青绿（绢本山水）：背景#FAFAF7+文字#1A1A1A+accent#2E8B7A，13个文件颜色替换，面板改白色毛玻璃，云雾透明度降低，VISUAL-STYLE-GUIDE.md重写
|
||||||
@@ -45,10 +52,3 @@
|
|||||||
- [CL-20260413-0930] System Prompt 加入"禁止模拟工具调用"约束，防止 DeepSeek 用文字模拟生图而不调用工具
|
- [CL-20260413-0930] System Prompt 加入"禁止模拟工具调用"约束，防止 DeepSeek 用文字模拟生图而不调用工具
|
||||||
- [CL-20260413-0900] 非 vision + 参考图场景：不再绝对禁止风格词，改为"不自行猜测但保留用户明确指定的风格"
|
- [CL-20260413-0900] 非 vision + 参考图场景：不再绝对禁止风格词，改为"不自行猜测但保留用户明确指定的风格"
|
||||||
- [CL-20260413-0800] 修复 InstantStyle ReadTimeout + 多次生成丢失参考图：wait 改 False 走纯轮询 + 不再清除 ref_image_url
|
- [CL-20260413-0800] 修复 InstantStyle ReadTimeout + 多次生成丢失参考图：wait 改 False 走纯轮询 + 不再清除 ref_image_url
|
||||||
- [CL-20260413-0730] 修复生图失败后 LLM 重试丢失参考图：ref_image_url 改为仅在成功产出图片后才清除
|
|
||||||
- [CL-20260413-0700] 修复 InstantStyle 生图 422 + ReadTimeout：`wait=300` 超限改为 `wait=60`，SDK 超时自动 fallback 轮询
|
|
||||||
- [CL-20260413-0630] 修复 Replicate SDK 不走代理 + 超时不够：注入 HTTPS_PROXY 到 transport + read 300s / connect 30s，解决 ConnectTimeout 连环错误
|
|
||||||
- [CL-20260413-0600] 新增 InstantStyle 模型（强风格迁移），与 Kolors 并列为参考图模型选项，block_mode=style-only
|
|
||||||
- [CL-20260413-0540] 非 vision LLM + 参考图时禁止猜测风格，prompt 只描述内容不写画风，风格交由 IP-Adapter 处理
|
|
||||||
- [CL-20260413-0520] 多图生成改为单次 API 调用（利用模型原生批量参数），避免速率限制 + 修复空错误信息显示
|
|
||||||
- [CL-20260413-0500] 图片生成后在对话中显示实际使用的模型名称（如"由 Kolors IP-Adapter 生成"），便于模型溯源
|
|
||||||
|
|||||||
@@ -1,8 +1,43 @@
|
|||||||
# Dev Changelog — Recent
|
# Dev Changelog — Recent
|
||||||
|
|
||||||
最近 ~10 次改动的摘要记录，按时间倒序排列。
|
最近 ~10 次改动的摘要记录，按时间倒序排列。
|
||||||
当 Agent 检测到当前任务与近期改动相关时自动读取。
|
当 Agent 检测到当前任务与近期改动相关时自动读取。
|
||||||
|
|
||||||
|
### [CL-20260420-2237] 2026-04-20 — 前端一次性铺开文档中心 / 3D / 动作三大功能 UI（占位 + Phase 2 徽章）
|
||||||
|
- **tags**: 前端, UI, 文档中心, 3D, 动作, 命令面板, 工作台, 资源库, 占位, react-markdown, model-viewer
|
||||||
|
- **affected_files**: types.ts, placeholder-store.ts, app-context.tsx, layout.tsx, top-nav.tsx, app/docs/page.tsx, components/docs/*, task-type-tabs.tsx, workbench/params-3d.tsx, workbench/params-motion.tsx, app/page.tsx, task-card.tsx, detail/model-3d-panel.tsx, detail/motion-panel.tsx, app/gallery/page.tsx, motion-presets.ts
|
||||||
|
- **summary**: 按用户要求一次性把"文档管理中心（类似 Cursor）/ 3D 模型生成 / 动作生成"的界面与交互全部用占位实现落地。文档中心：`/docs` 三栏（DocTree+Tabs+Editor+Outline），textarea+react-markdown+remark-gfm 编辑预览，`[[asset:id]]` 在正文内渲染为资产卡片，AssetPicker 浮层 + Ctrl/Cmd+K CommandPalette 全站搜索。工作台：TaskTypeTabs 切 2D/3D/动作，按类型显示 Params3D（管道/视图/分辨率）或 ParamsMotionBar（模型/帧数/fps/循环/输出/角色/动作描述）；TaskCard 加 variant 区分颜色图标和 3D/动作专有字段。结果详情：Model3DPanel（多视图+360°占位+`<model-viewer>` 三模式，通道切 color/normal/stylized）、MotionPanel（视频/帧序列双模式+scrubber+MP4/GIF 下载占位）。资源库：顶部模态 Tab（图片/3D/动作）+ 计数与 Phase 徽章，3D/动作网格叠徽章+视角/帧数，动作卡片 hover 自动播放视频。`<model-viewer>` 通过 `next/script` lazyOnload 引入，真实管线接入时只换数据源。一次性写完避免后续反复返工；`npx next build` 通过。
|
||||||
|
|
||||||
|
### [CL-20260420-1800] 2026-04-20 — Mesh Pipeline Phase 3 风格还原接入（IP-Adapter + ControlNet）
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, 风格还原, IP-Adapter, ControlNet, style_restorer, Phase 3
|
||||||
|
- **affected_files**: config.py, services/style_restorer.py (新增), services/view_transform.py, scripts/test_style_restore.py (新增), VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **summary**: 按 SPEC §4 Phase 3 落地 Mesh Pipeline 最后一段。在 `IMAGE_MODELS` 以 `internal=True` 注册 `chigozienri/ip_adapter-sdxl-controlnet-depth`（$0.07/张 ~72s，L40S），`get_image_models_list()` 改过滤 internal 防污染前端下拉；新增 helper `get_style_restore_model_id()`。新增 `services/style_restorer.py`：`restore()` 调 Replicate（`image`=用户原图做 IP-Adapter 风格参考，`controlnet_input`=Stage 2 的 normal 帧做结构约束，即 SPEC §1.4 的"路 A"），`restore_batch()` 用 `asyncio.Semaphore(3)` 批量重绘防 Replicate rate limit。`view_transform._transform_view_mesh` 接入 Stage 3：`preserve_style=True` 时对每帧调 restore_batch，**单帧失败自动回退为 Stage 2 color 帧且不阻塞整体**（error 字段挂出原因），与"Stage 2 失败不影响 Stage 1"的独立交付设计一致；`images[i]` 新增 `color_url/restyled/restyle_error` 字段，`_stage` 升级为 `stage3 (N/M restyled)`。新增 `scripts/test_style_restore.py` 供 Checkpoint 3：支持 `--single` 冒烟（$0.07）/全量（$0.42）、`--scale/--cn-scale` 覆盖参数、默认自动挑最新一组 normal 帧，复用 Phase 2 产物无需再跑 Trellis。默认参 scale=0.75 / controlnet=0.8，P3-4 调参由用户验收阶段确认。一次完整 6 视角请求 ~$0.46 / ~105s。
|
||||||
|
|
||||||
|
### [CL-20260420-1700] 2026-04-20 — Mesh Pipeline Phase 2 抽帧 + combined_video 左右切分
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, Trellis, ffmpeg, imageio-ffmpeg, PIL, video_frame_extractor, Phase 2
|
||||||
|
- **affected_files**: video_frame_extractor.py (新增), view_transform.py, requirements.txt, scripts/test_frame_extract.py (新增), VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **summary**: 按 SPEC §4 Phase 2 落地 Mesh Pipeline 的阶段 2 抽帧。系统 ffmpeg 未装，改用 `imageio-ffmpeg==0.5.1` 自带的 Windows 静态二进制（`ffmpeg-win64-v4.2.2.exe`，wheel 22.6MB，免系统依赖）。新增 `services/video_frame_extractor.py` 实现 `extract_by_azimuth(combined_video_path, azimuths, elevations, total_rotation_deg=360)`：策略采用"一次全帧抽取到临时目录 + 按帧索引挑 + PIL 按中线切左右半"，比 `-ss` 逐帧抽更稳（免 keyframe 对齐），5s 视频成本可忽略；ffmpeg + PIL 阻塞部分用 `run_in_executor` 丢到线程池。`view_transform._transform_view_mesh` 串接 Stage1→Stage2，默认 `azimuths=[0,60,120,180,240,300]`，返回 `images[{url,azimuth,elevation,normal_url,frame_idx}]`；Stage 2 失败不会把整体置为失败（Stage 1 的 mesh/video 仍有交付价值，单独填 `error` 字段）。新增 `scripts/test_frame_extract.py` 供用户复用已有 `generated/trellis_combined_*.mp4` 做 Checkpoint 2 验收，无需再花钱跑 Trellis。Agent 已自测 120 帧 combined_video：6 视角映射到 frame_idx=0/20/40/60/80/100（完全均匀）+ 所有切图 512×512 方形。等用户 Checkpoint 2 验收后开 Phase 3（IP-Adapter+ControlNet 风格还原）。
|
||||||
|
|
||||||
|
### [CL-20260420-1600] 2026-04-20 — Mesh Pipeline Phase 1 接入 Trellis（阶段 1 地基）
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, Trellis, Replicate, services, config, tools, Phase 1
|
||||||
|
- **affected_files**: mesh_generator.py (新增), view_transform.py, config.py, tools.py, scripts/test_trellis.py (新增), VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **summary**: 按 SPEC §4 Phase 1 落地 Mesh Pipeline 第二条视角变换管道的阶段 1。新增 `services/mesh_generator.py` 封装 Trellis 调用（`firtoz/trellis:e8f6c452...`）+ httpx 下载 `.glb/color_video/normal_video` 到 `generated/`；`config.py` 在 `VIEW_TRANSFORM_MODELS` 注册 `trellis`（enabled）和 `hunyuan3d`（enabled=False 占位），给所有条目加 `pipeline` 字段；`view_transform.py` 按 `pipeline` 分流 grid/mesh，mesh 阶段 1 只返回 mesh_url + color_video + normal_video，images 暂空；`tools.py` 的 `transform_view` 工具扩 `model_id/azimuths/preserve_style`。另新增 `scripts/test_trellis.py` 作为独立验收入口。Zero123++ 现有行为完全不变。等用户手跑脚本验收后开 Phase 2（ffmpeg 抽帧）。
|
||||||
|
|
||||||
|
### [CL-20260420-1530] 2026-04-20 — 写入 Mesh-Pipeline 视角变换方案 SPEC（跨会话实施计划）
|
||||||
|
- **tags**: 视角变换, Mesh Pipeline, Trellis, Hunyuan3D-2, SPEC, 方案
|
||||||
|
- **affected_files**: docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
|
||||||
|
- **summary**: 针对"Zero123++ 只出 6 固定视角 + 建筑大角度易崩"的痛点，规划第二条视角变换路径 Mesh Pipeline。三段式：Trellis 生 .glb + 360° color_video（$0.041/30s） → ffmpeg 按 azimuth 抽帧 → `chigozienri/ip_adapter-sdxl-controlnet-depth` 用原图做 IP-Adapter 风格还原。文档含三个 Replicate 模型的版本 ID/OpenAPI schema、config 扩展设计、6 个 Phase 可独立执行任务清单、跨会话恢复指引。Hunyuan3D-2 + pyrender 自由相机留作 Phase 5 二期可选。一期工程量 ~5h，单次总成本 ~$0.46/~105s。
|
||||||
|
|
||||||
|
### [CL-20260420-1501] 2026-04-20 — 后端增加 watchfiles 依赖，修复 Windows uvicorn --reload 失效
|
||||||
|
- **tags**: uvicorn, watchfiles, 热重载, Windows, reload, requirements
|
||||||
|
- **affected_files**: requirements.txt, requirements-lock.txt
|
||||||
|
- **summary**: 排查"Zero123++ 切图还是错位"时发现：CL-20260420-1212 的修复在磁盘上完全正确，但后端 uvicorn 进程是 11:55 启动从未 reload。根因是 venv 里 `watchfiles` 和 `watchdog` 都没装，`--reload` 退化成 StatReload 轮询式 reloader，在 Windows + 深层子目录 + 新建文件 (`view_transform.py`) 场景下基本失效。解决：pip 安装 `watchfiles==0.24.0` 并写入 requirements 两个文件。**仅装依赖不会对当前进程生效，必须 kill + 重启后端**。踩坑记为 PF-20260420-1501。
|
||||||
|
|
||||||
|
### [CL-20260420-1212] 2026-04-20 — 修复 Zero123++ 视角切图布局反转（3×2→2×3）
|
||||||
|
- **tags**: Zero123++, 视角变换, 切图, bug修复, grid_layout
|
||||||
|
- **affected_files**: config.py, view_transform.py
|
||||||
|
- **summary**: 用户反馈 `transform_view` 输出的 6 张视角图严重错位（每张呈窄长条、上下拼两个物体）。根因是 `jd7h/zero123plusplus` Replicate 部署版实际输出 **2 列 × 3 行** 的高图，但 `config.py` 里按官方 README "3×2 grid" 字面意思配成了 `cols=3, rows=2`。修复：(1) `grid_layout` 改为 `{"cols": 2, "rows": 3}`；(2) `_split_grid_image` 新增健壮性保护——假定单视角正方形，若配置 ratio 与实际图像 ratio 差异 >20%，自动交换 cols/rows 并打 warning，让未来换其他视角变换模型时免疫类似布局歧义。踩坑已记录 PF-20260420-1212。
|
||||||
|
|
||||||
### [CL-20260417-1510] 2026-04-17 — Cloudflare 穿透脚本兼容 PS5.1 + 本地 cloudflared
|
### [CL-20260417-1510] 2026-04-17 — Cloudflare 穿透脚本兼容 PS5.1 + 本地 cloudflared
|
||||||
- **tags**: 内网穿透, cloudflared, PowerShell, start-tunnel, env
|
- **tags**: 内网穿透, cloudflared, PowerShell, start-tunnel, env
|
||||||
- **affected_files**: art-agent/start-tunnel.ps1, .gitignore
|
- **affected_files**: art-agent/start-tunnel.ps1, .gitignore
|
||||||
@@ -68,253 +103,3 @@
|
|||||||
- **affected_files**: image_gen.py, config.py
|
- **affected_files**: image_gen.py, config.py
|
||||||
- **summary**: 新增 GeminiNativeImageProvider，通过向量引擎中转调用 Gemini 原生 `/v1beta/models/{model}:generateContent` 接口（非 OpenAI 兼容的 images/edit）。支持文字+图片混合输入（最多 14 张参考图），图片以 inline_data base64 内联传入。新增 `_resolve_image_base64` 工具函数统一处理 data URI 和本地路径到 (mime, b64) 的解析。config.py 中 Gemini 模型改用 `gemini_native` provider 并恢复 `supports_ref_image: True`。Provider 注册表新增 `gemini_native` 条目。
|
- **summary**: 新增 GeminiNativeImageProvider，通过向量引擎中转调用 Gemini 原生 `/v1beta/models/{model}:generateContent` 接口（非 OpenAI 兼容的 images/edit）。支持文字+图片混合输入（最多 14 张参考图），图片以 inline_data base64 内联传入。新增 `_resolve_image_base64` 工具函数统一处理 data URI 和本地路径到 (mime, b64) 的解析。config.py 中 Gemini 模型改用 `gemini_native` provider 并恢复 `supports_ref_image: True`。Provider 注册表新增 `gemini_native` 条目。
|
||||||
|
|
||||||
### [CL-20260416-0620] 2026-04-16 — 修复拖拽上传重复 + Gemini 改回不支持参考图 + images.edit 参数修正
|
|
||||||
- **tags**: bug修复, 拖拽, Gemini, 向量引擎, images.edit, config
|
|
||||||
- **affected_files**: chat-input.tsx, config.py, image_gen.py
|
|
||||||
- **summary**: 三个问题修复：(1) 拖拽到 ChatInput 区域时事件冒泡导致 page.tsx 和 ChatInput 各触发一次上传 → ChatInput handleDrop/handleDragOver 加 stopPropagation；(2) 向量引擎 Gemini 图片编辑走原生 generateContent 接口而非 OpenAI 兼容 images/edits，对 Gemini 调用 images.edit 返回 500 → Gemini 改回 supports_ref_image=False；(3) images.edit 端点不支持 quality 参数 → 从 _edit_with_refs 中移除。
|
|
||||||
|
|
||||||
### [CL-20260416-0600] 2026-04-16 — 多张参考图全链路支持
|
|
||||||
- **tags**: 前端, 后端, 参考图, 多图, OpenAI, images.edit, Provider, API, Agent Loop
|
|
||||||
- **affected_files**: chat-input.tsx, page.tsx, chat-messages.tsx, api.ts, types.ts, chat.py, loop.py, tools.py, image_gen.py, config.py
|
|
||||||
- **summary**: 从单张参考图扩展为多张参考图全链路支持。前端：ChatInput 改为多图状态数组+file input multiple+多图预览/删除/拖拽；API层 sendChat 改为 ref_image_urls: string[]；消息气泡和沿用逻辑适配多图。后端：chat.py 新增 ref_image_urls JSON 数组参数（兼容旧 ref_image_url）；Agent Loop 多图注入 vision LLM 上下文；OpenAIImageProvider 有参考图时改用 images.edit 端点（支持最多16张）；Replicate 取首张兼容；GPT Image 1.5 和 Gemini 注册表标记 supports_ref_image=True。
|
|
||||||
|
|
||||||
### [CL-20260416-0510] 2026-04-16 — 生图模型新增 Gemini 3.1 Flash Image
|
|
||||||
- **tags**: 后端, 生图模型, Gemini, 向量引擎, config
|
|
||||||
- **affected_files**: config.py, .env
|
|
||||||
- **summary**: IMAGE_MODELS 注册表新增 gemini-3.1-flash-image（model_id: gemini-3.1-flash-image-preview），provider 为 openai，复用 OpenAIImageProvider 走向量引擎中转。无需新增 Provider 代码。
|
|
||||||
|
|
||||||
### [CL-20260416-0500] 2026-04-16 — 全区域拖拽添加参考图
|
|
||||||
- **tags**: 前端, UX, 拖拽, 参考图, 上传
|
|
||||||
- **affected_files**: page.tsx, chat-input.tsx
|
|
||||||
- **summary**: 拖拽上传参考图区域从底部输入栏扩展到整个对话区域。ChatInput 改为 forwardRef 暴露 uploadFile 方法，main 区域处理拖放事件并调用。拖入时显示全屏覆盖层提示，用 dragCounter 防止子元素冒泡导致闪烁。
|
|
||||||
|
|
||||||
### [CL-20260416-0430] 2026-04-16 — 接入 GPT Image 1.5 生图模型（向量引擎中转）
|
|
||||||
- **tags**: 后端, 生图模型, GPT-Image, OpenAI, 向量引擎, provider
|
|
||||||
- **affected_files**: image_gen.py, config.py, .env
|
|
||||||
- **summary**: 新增 OpenAIImageProvider，通过向量引擎 API 中转调用 `/v1/images/generations` 端点。IMAGE_MODELS 注册表新增 gpt-image-1.5（provider: openai），支持 size/quality 参数和 URL/base64 双格式返回。
|
|
||||||
|
|
||||||
### [CL-20260416-0400] 2026-04-16 — Session 级参考图自动沿用 + 缺参考图前置校验
|
|
||||||
- **tags**: 前端, 后端, 参考图, UX, InstantStyle, 风格迁移
|
|
||||||
- **affected_files**: page.tsx, chat-input.tsx, image_gen.py
|
|
||||||
- **summary**: 用户发送带参考图的消息后，前端在 session 级别记住该参考图 URL，后续消息自动沿用（输入框显示"沿用上次参考图"提示条，可清除）。解决切换 InstantStyle 后无参考图导致 "No input, Save money" 的问题。后端对需要参考图但未收到的模型统一返回友好错误。
|
|
||||||
|
|
||||||
### [CL-20260416-0300] 2026-04-16 — System Prompt 禁止 LLM 嵌入图片链接
|
|
||||||
- **tags**: 后端, agent-loop, system-prompt, LLM行为约束
|
|
||||||
- **affected_files**: loop.py
|
|
||||||
- **summary**: LLM（GPT 系列）在收到 generate_image 工具返回的本地路径后，自行拼凑 `sandbox:/generated/xxx.png` Markdown 图片链接。前端图片展示由 image_result SSE 事件独立处理，文字中的链接无效且多余。在 System Prompt 注意事项中新增禁止嵌入图片 Markdown 的约束。
|
|
||||||
|
|
||||||
### [CL-20260416-0245] 2026-04-16 — 修复三点菜单 z-index 层级问题
|
|
||||||
- **tags**: 前端, UI, sidebar, 菜单, z-index
|
|
||||||
- **affected_files**: session-list.tsx
|
|
||||||
- **summary**: 三点菜单原用 fixed 定位在侧栏右侧弹出，被主内容区遮挡。改为 inline 在会话项正下方展开，模型子菜单改为折叠式内联列表（带 max-h 滚动），全部在侧栏内部完成，不再溢出。移除了 menuPos 状态和 fixed 定位逻辑。
|
|
||||||
|
|
||||||
### [CL-20260416-0230] 2026-04-16 — LLM 注册表扩充 + 默认模型改 GPT-5.4
|
|
||||||
- **tags**: 后端, config, LLM, 模型注册表
|
|
||||||
- **affected_files**: config.py, .env
|
|
||||||
- **summary**: LLM_MODELS 从 3→7 个：新增 gpt-5.4、claude-sonnet-4-6、claude-opus-4-6、gemini-3.1-pro-preview、glm-4.7，全部走 vectorengine provider。默认模型从 gpt-4o-mini 改为 gpt-5.4。gpt-4o-mini/deepseek-chat 保留。
|
|
||||||
|
|
||||||
### [CL-20260416-0200] 2026-04-16 — 接入向量引擎中转 API + 对话级 LLM 模型切换
|
|
||||||
- **tags**: 后端, 前端, LLM, 向量引擎, 中转API, 模型切换, config, UI, session
|
|
||||||
- **affected_files**: config.py, loop.py, chat.py, .env, types.ts, api.ts, app-context.tsx, session-list.tsx, page.tsx
|
|
||||||
- **summary**: 新增 LLM_MODELS 注册表（gpt-4o-mini/gpt-4o/deepseek-chat），provider 分发为 vectorengine（中转）和 deepseek（直连）。loop.py 改为按 provider 创建 AsyncOpenAI 客户端，vision 检测从注册表读取。chat.py 新增 llm_model 参数和 GET /api/llm-models 端点。前端 Session 新增 llmModel 字段，侧栏三点菜单支持模型选择子菜单，sendChat 传递 llm_model。
|
|
||||||
|
|
||||||
### [CL-20260416-0030] 2026-04-16 — 青绿山水风格改造：千里江山图色调 + 云烟雾气动效
|
|
||||||
- **tags**: 前端, UI改造, 视觉风格, 青绿山水, 千里江山图, CSS动画, 色彩体系, 云烟
|
|
||||||
- **affected_files**: globals.css, top-nav.tsx, sidebar.tsx, session-list.tsx, chat-messages.tsx, chat-input.tsx, image-grid.tsx, image-detail-panel.tsx, profile-modal.tsx, page.tsx, gallery/page.tsx, login/page.tsx, VISUAL-STYLE-GUIDE.md
|
|
||||||
- **summary**: 全站从 Cyberpunk 霓虹改为青绿山水风格。色彩替换为石青绿(#4DB8A4)/石绿蓝(#3A8FB7)/墨绿底色(#0C1210)。背景改为双层漂移云雾(60s+45s)。.glow-border hover 效果柔化为云烟缭绕(6s/宽弧段/blur 12px)。.glass-panel 加绿底渐变+增强模糊。新增 .fog-scroll 雾气滚动边缘。11 个组件硬编码颜色全部替换。VISUAL-STYLE-GUIDE.md 完全重写。
|
|
||||||
|
|
||||||
### [CL-20260415-2330] 2026-04-15 — 用户个人信息 + 记忆查看面板：右上角菜单弹窗
|
|
||||||
- **tags**: 前端, 后端, 用户信息, 记忆系统, Mem0, Modal, ProfileModal
|
|
||||||
- **affected_files**: api/memory.py, main.py, profile-modal.tsx, top-nav.tsx
|
|
||||||
- **summary**: 后端新建 GET /api/memory/list 端点（Mem0 get_all + run_in_executor），前端新建 ProfileModal 组件（glass-panel 风格居中弹窗），展示用户信息 + 按时间分组的记忆列表（只读）。TopNav 的 username 行改为可点击按钮，点击打开弹窗。
|
|
||||||
|
|
||||||
### [CL-20260415-2230] 2026-04-15 — 光影流动边框效果：导航活动项 + 活动会话项
|
|
||||||
- **tags**: 前端, CSS动画, 视觉效果, conic-gradient, 霓虹边框
|
|
||||||
- **affected_files**: globals.css, top-nav.tsx, session-list.tsx, sidebar.tsx
|
|
||||||
- **summary**: 用 @property + conic-gradient 实现旋转光影边框效果。双伪元素方案：::before 做渐变边框（mask-composite 裁内部），::after 做模糊扩散光晕。提供 .glow-border（动画）和 .glow-border-static（hover 静态发光）两个类，分别应用到导航活动 Tab 和活动会话项。
|
|
||||||
|
|
||||||
### [CL-20260415-2200] 2026-04-15 — 全站 UI 风格改造：Cyberpunk Dark Neon 主题
|
|
||||||
- **tags**: 前端, UI改造, 视觉风格, Cyberpunk, Neon, 毛玻璃, 全局样式
|
|
||||||
- **affected_files**: globals.css, page.tsx, gallery/page.tsx, login/page.tsx, top-nav.tsx, sidebar.tsx, session-list.tsx, tag-filter.tsx, chat-messages.tsx, chat-input.tsx, image-grid.tsx, model-selector.tsx, image-detail-panel.tsx, VISUAL-STYLE-GUIDE.md
|
|
||||||
- **summary**: 参考 SolCasino Dribbble 设计，全站从朴素暗色改为 Cyberpunk Dark Neon 风格。主色从紫色改为青绿霓虹(#00E5A0)，新增环境光晕背景、毛玻璃面板(backdrop-blur)、霓虹发光边框。所有组件统一升级圆角和过渡效果，图片卡片加 hover 缩放+发光。同时编写了完整的视觉风格文档。
|
|
||||||
|
|
||||||
### [CL-20260414-2350] 2026-04-14 — 修复登录后 useApp must be used within AppProvider 报错
|
|
||||||
- **tags**: bug修复, 前端, 认证, AppProvider, 初始化时序
|
|
||||||
- **affected_files**: app-context.tsx
|
|
||||||
- **summary**: AppProvider 在 `!initialized` 时不提供 context 但渲染了需要 useApp() 的子组件。修复：已认证但未初始化时显示加载状态，未认证时才渲染裸 children（/login）。
|
|
||||||
|
|
||||||
### [CL-20260414-2340] 2026-04-14 — 用 pwdlib (Argon2id) 替换 passlib (bcrypt)，彻底解决兼容性问题
|
|
||||||
- **tags**: 重构, 安全, 密码哈希, Argon2, pwdlib, passlib, 依赖升级
|
|
||||||
- **affected_files**: auth.py, requirements.txt, docs/art-agent/USER-SYSTEM.md
|
|
||||||
- **summary**: passlib 已停止维护且与 bcrypt 5.x 不兼容。替换为 pwdlib[argon2,bcrypt]，新密码用 Argon2id，旧 bcrypt 哈希仍可验证。不再需要锁定 bcrypt 版本。
|
|
||||||
|
|
||||||
### [CL-20260414-2330] 2026-04-14 — 修复 passlib + bcrypt 5.x 兼容性问题，锁定 bcrypt<4.1
|
|
||||||
- **tags**: bug修复, 依赖, bcrypt, passlib, 用户系统
|
|
||||||
- **affected_files**: requirements.txt, docs/art-agent/USER-SYSTEM.md
|
|
||||||
- **summary**: passlib 1.7.4 与 bcrypt 5.0.0 不兼容（`__about__` 移除 + 密码长度 ValueError），后端启动报错。降级 bcrypt 到 4.0.1 并在 requirements.txt 中锁定 `>=4.0.1,<4.1`。同时在用户系统文档故障排除中补充此问题。
|
|
||||||
|
|
||||||
### [CL-20260414-2300] 2026-04-14 — 用户系统：管理员邀请制 + JWT 认证 + 数据按用户隔离
|
|
||||||
- **tags**: 用户系统, 认证, JWT, SQLite, 数据隔离, 多用户, 安全
|
|
||||||
- **affected_files**: db.py, auth.py, api/auth.py, api/admin.py, chat.py, main.py, loop.py, auth-context.tsx, auth-guard.tsx, api.ts, store.ts, app-context.tsx, layout.tsx, login/page.tsx, top-nav.tsx, model-selector.tsx, requirements.txt, .env.example
|
|
||||||
- **summary**: 后端新增 SQLite 用户表 + JWT 认证（access+refresh）+ 管理员/普通用户路由，所有 API 加鉴权，Mem0 user_id 改为真实用户 ID。前端新增登录页 + AuthProvider/AuthGuard + 401 自动跳转 + localStorage 按用户 ID 隔离。TopNav 新增用户菜单。首次启动自动创建 admin。
|
|
||||||
|
|
||||||
### [CL-20260414-2230] 2026-04-14 — 对话区域新增"回到底部"浮动按钮
|
|
||||||
- **tags**: 前端, UX, 滚动, 浮动按钮
|
|
||||||
- **affected_files**: art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: 长对话中不在底部时，右下角显示向下箭头按钮，点击平滑滚到最新消息。复用 scroll 监听器检测距底部距离（>200px 显示），切换会话后也同步按钮状态。
|
|
||||||
|
|
||||||
### [CL-20260414-2220] 2026-04-14 — 修复长对话切换回来滚动位置上移：scroll 事件实时保存取代 effect 延迟保存
|
|
||||||
- **tags**: 前端, bug修复, 滚动, 多会话, UX, scroll 事件
|
|
||||||
- **affected_files**: art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: effect 中保存 scrollTop 时 DOM 已变为短对话内容，浏览器 clamp scrollTop 导致保存值偏小。改用 scroll 事件实时记录位置，确保在任何 DOM 变更之前数据已正确保存。
|
|
||||||
|
|
||||||
### [CL-20260414-2210] 2026-04-14 — 修复会话切换时滚动位置跳动：时序竞争 + 抑制切换期间 smooth scroll
|
|
||||||
- **tags**: 前端, bug修复, 滚动, 多会话, UX, 时序
|
|
||||||
- **affected_files**: art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: CL-20260414-2200 的 rAF 恢复时序不可靠——React 可能还没渲染新会话内容，scrollHeight 是旧值。拆为两个 effect（保存+标记 / 等 messages 更新后恢复），新增 `isSwitching` 抑制切换期间的 smooth scroll 干扰，instant 模式改为同步赋值 `scrollTop`。
|
|
||||||
|
|
||||||
### [CL-20260414-2200] 2026-04-14 — 修复多会话滚动位置共享 bug：per-session 独立记录 + 切换恢复
|
|
||||||
- **tags**: 前端, bug修复, 滚动, 多会话, UX
|
|
||||||
- **affected_files**: art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: 所有会话共用同一 scrollRef，切换时不保存/恢复 scrollTop。修复：新增 `scrollPositions` Map 按 sessionId 记录滚动位置，`useEffect` 监听 `activeSessionId` 变化时保存旧位置、恢复新位置（有记录则恢复，无记录则 scrollToBottom）。`scrollToBottom` 改为 useCallback + 支持 instant 模式。
|
|
||||||
|
|
||||||
### [CL-20260413-2320] 2026-04-13 — 集成 Mem0 记忆系统：滑动窗口 + 跨会话长期记忆
|
|
||||||
- **tags**: Mem0, 记忆系统, 上下文管理, 长期记忆, Ollama, embedding, 滑动窗口
|
|
||||||
- **affected_files**: app/memory.py, app/agent/loop.py, app/config.py, app/api/chat.py, requirements.txt, .env, frontend/src/lib/api.ts, frontend/src/app/page.tsx
|
|
||||||
- **summary**: 集成 Mem0 OSS 作为统一记忆方案。DeepSeek 做事实提取，Ollama nomic-embed-text 做本地 embedding，Qdrant 文件模式做向量存储。agent loop 新增滑动窗口（MAX_RECENT_TURNS=20）、记忆检索注入 system prompt、异步事实存储。前端传递 session_id 实现会话级记忆作用域。不做静默降级，所有错误显式报告。
|
|
||||||
|
|
||||||
### [CL-20260413-1130] 2026-04-13 — 修复 SDXL 模型 404 错误：补全 Replicate 版本 hash
|
|
||||||
- **tags**: bug修复, Replicate, SDXL, 模型配置, 404
|
|
||||||
- **affected_files**: art-agent/backend/app/config.py
|
|
||||||
- **summary**: SDXL 调用 Replicate 404，根因同 Kolors（CL-20260413-0440）：非 Flux 官方模型需要 `owner/model:version_hash` 完整格式。将 `stability-ai/sdxl` 补全为 `stability-ai/sdxl:39ed52f2...e08b`。
|
|
||||||
|
|
||||||
### [CL-20260413-1100] 2026-04-13 — 修复切换模型后 LLM 仍声称使用旧模型名
|
|
||||||
- **tags**: Agent Loop, system prompt, 模型选择, LLM 幻觉
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: System Prompt 不含模型信息，LLM 从对话历史幻觉旧模型名。修复：在 system prompt 末尾动态注入当前模型名 + 强调忽略历史中的旧记录，假生成重试消息也附带模型名。debug 日志验证传递链路正确，问题仅在 LLM 文字层。
|
|
||||||
|
|
||||||
### [CL-20260413-1030] 2026-04-13 — Agent Loop 假生成检测 + 自动重试机制
|
|
||||||
- **tags**: Agent Loop, DeepSeek, function calling, 防幻觉, 自动修复
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: DeepSeek 无视 prompt 约束，仍用文字模拟生图。新增代码层面检测：LLM 纯文字回复中命中"已生成"等关键词 >= 2 次时，自动注入纠正消息强制重试调用工具。重试消耗一次迭代配额。
|
|
||||||
|
|
||||||
### [CL-20260413-1000] 2026-04-13 — 助手消息气泡添加复制文本按钮
|
|
||||||
- **tags**: 前端, UX, chat-messages, 复制
|
|
||||||
- **affected_files**: art-agent/frontend/src/components/chat/chat-messages.tsx
|
|
||||||
- **summary**: 助手回复气泡下方新增复制文本按钮（hover 显示），点击通过 clipboard API 复制文本并显示 1.5s 对勾反馈。只对 assistant 消息展示。
|
|
||||||
|
|
||||||
### [CL-20260413-0930] 2026-04-13 — System Prompt 加入"禁止模拟工具调用"约束
|
|
||||||
- **tags**: prompt 工程, system prompt, DeepSeek, function calling, 防幻觉
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: DeepSeek 在多步生图任务中有时不调用工具而是用文字模拟"已生成"，导致前端收不到图片。在 System Prompt 注意事项中加入硬性约束："生成图片必须调用 generate_image 工具，禁止用文字模拟"。
|
|
||||||
|
|
||||||
### [CL-20260413-0900] 2026-04-13 — 非 vision + 参考图场景：尊重用户主动指定的风格意图
|
|
||||||
- **tags**: prompt 工程, IP-Adapter, 风格, system prompt, UX
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: SYSTEM_PROMPT 和非 vision hint 中对风格关键词的禁止从"绝对禁止"改为"不自行猜测，但用户明确指定则保留到 prompt 中"。之前的绝对性措辞导致 LLM 即使用户主动写了"赛博朋克风"也会丢弃。修正后 IP-Adapter 风格迁移与用户文字风格可叠加。
|
|
||||||
|
|
||||||
### [CL-20260413-0800] 2026-04-13 — 修复 InstantStyle ReadTimeout + 多次生成丢失参考图
|
|
||||||
- **tags**: bug修复, Replicate, InstantStyle, timeout, 参考图, Agent Loop, wait
|
|
||||||
- **affected_files**: art-agent/backend/app/services/image_gen.py, art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: 运行时日志证实两个问题：(1) `wait=60` 时 SDK 内部 `read=60.5s` timeout 覆盖客户端 300s timeout，上传 1.6MB base64 + 等待初始响应超过 60s → ReadTimeout。改为 `wait=False`，create 请求立即返回 prediction ID，SDK 自动走 `prediction.async_wait()` 轮询，轮询用客户端级 read=300s timeout。(2) 成功生成后清除 ref_image_url 导致后续工具调用丢失参考图（InstantStyle 返回 "No input, Save money"）。完全移除清除逻辑，ref_image_url 在整个对话期间保持有效。
|
|
||||||
|
|
||||||
### [CL-20260413-0730] 2026-04-13 — 修复生图失败后 LLM 重试丢失参考图
|
|
||||||
- **tags**: bug修复, Agent Loop, 参考图, InstantStyle, ref_image_url
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: LLM 第一次生图工具调用失败后重试时，参考图丢失。InstantStyle 返回 "No input, Save money"。根因：`loop.py` 在每轮工具调用结束后无条件清除 `ref_image_url`。修复：改为只在本轮至少有一次成功产出图片时才清除，失败时保留参考图供 LLM 重试。
|
|
||||||
|
|
||||||
### [CL-20260413-0700] 2026-04-13 — 修复 InstantStyle 生图 422 + ReadTimeout：wait 参数超限
|
|
||||||
- **tags**: bug修复, Replicate, InstantStyle, API参数, async_run, timeout
|
|
||||||
- **affected_files**: art-agent/backend/app/services/image_gen.py
|
|
||||||
- **summary**: InstantStyle 生图 422（`Prefer: wait=x must be 1-60`）+ ReadTimeout（61.4s）。两个问题同根因：`async_run(wait=300)` 超出 API 限制，改为 `wait=True` 后 SDK 内部 60.5s timeout 覆盖了客户端 300s timeout。最终改为 `wait=60`（API 最大合法值），初始请求 60s 内未完成则 SDK 自动 fallback 到异步轮询，轮询用客户端级 read=300s timeout。
|
|
||||||
|
|
||||||
### [CL-20260413-0630] 2026-04-13 — 修复 Replicate SDK 不走代理 + 超时不够
|
|
||||||
- **tags**: bug修复, Replicate, InstantStyle, 代理, httpx, 超时
|
|
||||||
- **affected_files**: art-agent/backend/app/services/image_gen.py
|
|
||||||
- **summary**: Replicate SDK 内部显式传 `transport` 给 httpx，绕过了环境变量代理配置导致 ConnectTimeout，且默认 read 30s 不够 InstantStyle 的 ~128s。修复：`_make_replicate_client()` 工厂函数从 `HTTPS_PROXY` 读取代理注入 `AsyncHTTPTransport(proxy=...)`，read 300s / connect 30s。`_download_image` 同步加了代理。
|
|
||||||
|
|
||||||
### [CL-20260413-0600] 2026-04-13 — 新增 InstantStyle 模型：强风格迁移选项
|
|
||||||
- **tags**: 模型注册, InstantStyle, 风格迁移, IP-Adapter
|
|
||||||
- **affected_files**: art-agent/backend/app/config.py
|
|
||||||
- **summary**: 注册 InstantStyle（`jyoung105/instant-style`）到模型注册表，`block_mode: "style-only"` + `style_strength: 1.0`，通过 `ref_image_param: "style_image"` 适配现有抽象。与 Kolors 并列为参考图模型，提供强风格迁移能力。
|
|
||||||
|
|
||||||
### [CL-20260413-0540] 2026-04-13 — 非 vision LLM + 参考图时禁止猜测风格
|
|
||||||
- **tags**: prompt 工程, IP-Adapter, 风格一致性, system prompt
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: 修改 system prompt 和非 vision 模型的参考图提示，明确禁止猜测画风。LLM 只描述画面内容，风格交给 IP-Adapter 从参考图提取。解决了 DeepSeek 看不到参考图时脑补 "pixel art" 导致生成结果与参考图风格不一致的问题。
|
|
||||||
|
|
||||||
### [CL-20260413-0520] 2026-04-13 — 多图生成改为单次 API 调用 + 修复空错误信息
|
|
||||||
- **tags**: 性能优化, Replicate, 速率限制, 错误处理, 模型配置
|
|
||||||
- **affected_files**: art-agent/backend/app/services/image_gen.py, art-agent/backend/app/config.py
|
|
||||||
- **summary**: 多图生成从 for 循环改为单次 API 调用（新增 `num_images_param` 配置），避免低余额账户的速率限制。同时修复空异常时 `[生成失败: ]` 信息丢失的问题，改为显示异常类型名和 repr。
|
|
||||||
|
|
||||||
### [CL-20260413-0500] 2026-04-13 — 生成图片后显示使用的模型名称
|
|
||||||
- **tags**: 模型溯源, SSE, 图片生成, 前端展示
|
|
||||||
- **affected_files**: art-agent/backend/app/services/image_gen.py, art-agent/backend/app/agent/tools.py, art-agent/backend/app/agent/loop.py, art-agent/frontend/src/lib/types.ts, art-agent/frontend/src/app/page.tsx, art-agent/frontend/src/components/chat/chat-messages.tsx
|
|
||||||
- **summary**: `generate_images` 返回 `GenerateResult`（含 model_name），SSE 事件携带模型名称，前端在图片下方和错误提示中展示。ChatMessage 新增 `modelName` 字段，归档后仍可溯源。
|
|
||||||
|
|
||||||
### [CL-20260413-0440] 2026-04-13 — 修复 Kolors IP-Adapter 模型 404 错误：补全 Replicate 版本 hash
|
|
||||||
- **tags**: bug修复, Replicate, Kolors, IP-Adapter, 模型配置
|
|
||||||
- **affected_files**: art-agent/backend/app/config.py
|
|
||||||
- **summary**: Kolors IP-Adapter 生图 404 的根因是 Replicate SDK 对社区模型需要 `owner/model:version_hash` 格式。在 config.py 中补全 kolors-ipadapter 的版本 hash 后，实测生图成功。
|
|
||||||
|
|
||||||
### [CL-20260413-0430] 2026-04-13 — 图片生成失败时将具体错误信息透传到前端
|
|
||||||
- **tags**: 错误处理, Agent Loop, SSE, 调试体验
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py, art-agent/frontend/src/app/page.tsx, art-agent/frontend/src/lib/api.ts
|
|
||||||
- **summary**: 新增 `tool_error` SSE 事件类型。Agent Loop 在工具执行产生错误时，额外 yield 一个 tool_error 事件携带具体报错信息；前端处理该事件并以 ⚠️ 前缀展示在对话流中。解决了之前工具失败时用户只能看到 LLM 模糊翻译、无法获取真实错误详情的问题。
|
|
||||||
|
|
||||||
### [CL-20260413-0330] 2026-04-13 — README 补充访问地址汇总 + 穿透管理文档
|
|
||||||
- **tags**: 文档, README, 穿透, Cloudflare, cloudflared
|
|
||||||
- **affected_files**: art-agent/README.md
|
|
||||||
- **summary**: README 新增"访问地址"章节（本机/局域网/外网三种场景表格），重写"远程访问（外网穿透）"章节，补充 cloudflared 安装指引（winget + 手动下载）、穿透管理操作表（启动/停止/查看状态/重启）、代理配置排错说明。
|
|
||||||
|
|
||||||
### [CL-20260412-2345] 2026-04-12 — 参考图上传独立化：进度条 + 状态反馈 + 失败重试
|
|
||||||
- **tags**: 前端, 后端, 参考图, 上传, UX, 进度反馈
|
|
||||||
- **affected_files**: art-agent/backend/app/api/chat.py, art-agent/frontend/src/lib/api.ts, art-agent/frontend/src/components/chat/chat-input.tsx, art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: 参考图从"随消息提交"改为"选中即独立上传"。后端新增 POST /api/upload-ref-image 端点；前端用 XMLHttpRequest 获取上传进度事件，ChatInput 显示环形进度条、成功/失败角标、失败可重选。sendChat 参数从 File 改为服务端路径。同时修复 file input 多次上传不重置的问题。
|
|
||||||
|
|
||||||
### [CL-20260412-2315] 2026-04-12 — 修复 Cloudflare Tunnel 跨域开发警告
|
|
||||||
- **tags**: 前端, 配置, Next.js, Cloudflare, 跨域
|
|
||||||
- **affected_files**: art-agent/frontend/next.config.ts
|
|
||||||
- **summary**: Next.js 检测到来自 trycloudflare.com 的跨域请求发出警告。在 next.config.ts 中添加 `allowedDevOrigins: ["*.trycloudflare.com"]` 消除警告，通配符覆盖所有 Quick Tunnel 随机域名。
|
|
||||||
|
|
||||||
### [CL-20260412-2300] 2026-04-12 — 集成 Kolors IP-Adapter，参考图可直接用于风格生成
|
|
||||||
- **tags**: 后端, 前端, IP-Adapter, 风格迁移, 参考图, 模型注册, Replicate, 架构
|
|
||||||
- **affected_files**: art-agent/backend/app/config.py, art-agent/backend/app/services/image_gen.py, art-agent/backend/app/agent/loop.py, art-agent/frontend/src/lib/types.ts, art-agent/frontend/src/components/chat/model-selector.tsx
|
|
||||||
- **summary**: 集成 Kolors IP-Adapter 模型（fofr/kolors-with-ipadapter，~$0.004/次），参考图通过 base64 data URI 直接传给 Replicate 的 IP-Adapter 参与风格生成。模型注册表新增 supports_ref_image / ref_image_param 通用字段，新增 IP-Adapter 模型只需加配置。to_data_uri 抽为公共函数供 loop.py 和 image_gen.py 共用。前端模型列表显示绿色"参考图"徽章。
|
|
||||||
|
|
||||||
### [CL-20260412-2230] 2026-04-12 — 用户消息气泡中显示参考图缩略图
|
|
||||||
- **tags**: 前端, 参考图, UX, chat-messages
|
|
||||||
- **affected_files**: art-agent/frontend/src/lib/types.ts, art-agent/frontend/src/app/page.tsx, art-agent/frontend/src/components/chat/chat-messages.tsx
|
|
||||||
- **summary**: 用户上传参考图后发送消息，之前聊天气泡中不显示参考图，无法确认是否成功附带。修复：ChatMessage 类型新增 refImageUrl 字段，page.tsx 构造用户消息时用 URL.createObjectURL 保存预览 URL，chat-messages.tsx 在用户消息气泡中渲染缩略图（最大 160×120px）。Blob URL 仅当前会话有效，不持久化。
|
|
||||||
|
|
||||||
### [CL-20260412-2200] 2026-04-12 — 修复 DeepSeek 不支持 image_url 导致参考图上传报错
|
|
||||||
- **tags**: bug修复, 后端, Agent Loop, vision, DeepSeek, 多模态
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/loop.py
|
|
||||||
- **summary**: 上传参考图时使用 OpenAI Vision 格式（`image_url` content type）发送给 DeepSeek API，但 DeepSeek 只支持 `text` 类型，导致 400 错误。修复：新增 vision 能力检测（基于模型名称关键词），不支持 vision 的模型改为文字提示方式告知 LLM 有参考图，参考图仍传给图像生成工具处理。
|
|
||||||
|
|
||||||
### [CL-20260412-2130] 2026-04-12 — 修复图片生成失败时前端显示破碎图标
|
|
||||||
- **tags**: bug修复, 前端, 后端, 图像生成, 错误处理
|
|
||||||
- **affected_files**: art-agent/backend/app/agent/tools.py, art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: Replicate API 调用失败（如余额不足 402）时，错误字符串 `[生成失败: ...]` 被混入 images 列表传给前端，导致 `<img>` 标签渲染破碎图标。修复：后端 tools.py 分离有效 URL 和错误信息为 images/errors 两个字段；前端 page.tsx 过滤掉以 `[` 开头的无效 URL，无有效图片时不渲染图片网格。
|
|
||||||
|
|
||||||
### [CL-20260412-2100] 2026-04-12 — 生图模型动态切换：Provider 抽象 + 前端模型选择器
|
|
||||||
- **tags**: 后端, 前端, 图像生成, 模型切换, Provider, 重构, Replicate
|
|
||||||
- **affected_files**: art-agent/backend/app/config.py, art-agent/backend/app/services/image_gen.py, art-agent/backend/app/api/chat.py, art-agent/backend/app/agent/loop.py, art-agent/backend/app/agent/tools.py, art-agent/backend/.env, art-agent/backend/.env.example, art-agent/frontend/src/lib/types.ts, art-agent/frontend/src/lib/api.ts, art-agent/frontend/src/components/chat/model-selector.tsx, art-agent/frontend/src/components/chat/chat-input.tsx, art-agent/frontend/src/app/page.tsx
|
|
||||||
- **summary**: 将图像生成从 Replicate 硬绑定重构为 Provider 抽象层。后端：config.py 新增 IMAGE_MODELS 注册表（flux-schnell / flux-dev / SDXL），image_gen.py 引入 ImageProvider 基类 + ReplicateProvider 实现，chat.py 新增 GET /api/models + POST /api/chat 增加 image_model 参数，agent loop / tools 全链路透传。前端：新建 ModelSelector 下拉组件集成到 ChatInput，每条消息可选不同模型，选择持久化到 localStorage。
|
|
||||||
|
|
||||||
### [CL-20260412-1800] 2026-04-12 — 移动端适配 + Cloudflare Tunnel 内网穿透
|
|
||||||
- **tags**: 前端, 响应式, 移动端, 部署, Cloudflare, 穿透, 配置
|
|
||||||
- **affected_files**: art-agent/frontend/src/app/layout.tsx, art-agent/frontend/src/app/globals.css, art-agent/frontend/src/app/page.tsx, art-agent/frontend/src/app/gallery/page.tsx, art-agent/frontend/src/components/sidebar/sidebar.tsx, art-agent/frontend/src/components/layout/top-nav.tsx, art-agent/frontend/src/components/detail/image-detail-panel.tsx, art-agent/frontend/src/components/chat/chat-messages.tsx, art-agent/frontend/src/components/chat/chat-input.tsx, art-agent/frontend/src/components/chat/image-grid.tsx, art-agent/frontend/src/lib/app-context.tsx, art-agent/frontend/next.config.ts, art-agent/start-tunnel.ps1, art-agent/README.md
|
|
||||||
- **summary**: 为实现"手机浏览器远程访问"做了两大块工作。(1) 移动端响应式适配：侧边栏改为固定定位抽屉式（md 以下），顶栏新增汉堡菜单，图片详情面板移动端全屏 overlay，气泡/输入框/Gallery 网格间距微调，hover 操作在移动端始终可见，默认小屏折叠侧边栏。(2) 穿透方案：安装 cloudflared，编写 start-tunnel.ps1 一键脚本自动创建双隧道 + 更新 .env.local + 退出时恢复。Next.js 图片白名单加 trycloudflare.com。uvicorn 改绑 0.0.0.0。路线 B（云服务器部署）记为延期方案。
|
|
||||||
|
|
||||||
### [CL-20260412-1530] 2026-04-12 — 修复 .env 配置加载时序问题
|
|
||||||
- **tags**: 后端, bug修复, 配置, dotenv, Python
|
|
||||||
- **affected_files**: art-agent/backend/app/main.py, art-agent/backend/app/config.py, art-agent/backend/app/agent/loop.py, art-agent/backend/app/services/image_gen.py, art-agent/backend/.env
|
|
||||||
- **summary**: 切换 DeepSeek 后报 "Model Not Exist"。根因：(1) load_dotenv() 在业务模块 import 之后执行，config.py 的模块级变量在 import 时就固化为默认值 gpt-4o-mini；(2) load_dotenv 默认 override=False 不覆盖已有环境变量。修复：load_dotenv(override=True) 提到所有 import 之前；config.py 常量改为函数式懒读取；.env base_url 改为不带 /v1。
|
|
||||||
|
|
||||||
### [CL-20260412-1500] 2026-04-12 — 品牌重命名 EPEEKit + API 配置集中化
|
|
||||||
- **tags**: EPEEKit, 品牌, 配置, 后端, 前端, 重构
|
|
||||||
- **affected_files**: art-agent/frontend/src/app/layout.tsx, art-agent/frontend/src/components/layout/top-nav.tsx, art-agent/frontend/src/app/page.tsx, art-agent/frontend/src/lib/store.ts, art-agent/frontend/src/app/gallery/page.tsx, art-agent/frontend/src/components/detail/image-detail-panel.tsx, art-agent/frontend/src/components/chat/image-grid.tsx, art-agent/frontend/package.json, art-agent/backend/app/main.py, art-agent/backend/app/config.py, art-agent/backend/app/agent/loop.py, art-agent/backend/app/services/image_gen.py, art-agent/backend/.env, art-agent/backend/.env.example, art-agent/README.md
|
|
||||||
- **summary**: 应用正式命名为 "EPEEKit"，全部用户可见文案 + 文件名前缀 + localStorage 键名统一替换。后端新增 config.py 集中管理 LLM_MODEL、IMAGE_MODEL 等原硬编码配置，.env 重组为带注释的分组结构，切换 LLM 只需改 3 个环境变量。同时新增 .env.example 模板和 Logo SVG。
|
|
||||||
|
|
||||||
|
|||||||
@@ -5,6 +5,27 @@ Agent 进入 Debug mode 或遇到运行时错误时自动检索匹配。
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
### [PF-20260420-1600] firtoz/trellis Replicate 部署版 schema 与 README 及官方 API 文档不一致
|
||||||
|
- **症状**: (1) 按 Replicate README example 用 `input={"image": uri}` 传单数 image → `422 Input validation failed: input: images is required`。改成 `images: [uri]` 后模型能跑，产出 model_file/combined_video/gaussian_ply/no_background_images。(2) 尽管 `generate_color=True` + `generate_normal=True` 都开，输出字典里 `color_video` 和 `normal_video` 字段**恒为 null**，只有 `combined_video` 这个"color 和 normal 左右并排的 mp4"才真正可用。
|
||||||
|
- **根因**: `firtoz/trellis:e8f6c45206993f297372f5436b90350817bd9b4a0d52d2a76df50c1c8afa2b3c` 这个 Replicate 部署版的实际输入/输出 schema 与 firtoz 在 Replicate README 里贴的 example、以及 microsoft/TRELLIS 官方仓库的 Python API 都不一样——输入字段是 `images`（数组）而不是 `image`（字符串），输出字段虽然声明了 `color_video` 和 `normal_video` 但该部署版恒给 null，只填 `combined_video`。很可能是部署者在包装层做了合并（省带宽/对象存储开销）但没同步 README。
|
||||||
|
- **解法**: (1) 输入字段固定传 `images: [uri]` 数组，即使只有 1 张图；(2) Phase 2 抽帧的数据源从 `combined_video` 切——每一帧的左半 = color、右半 = normal，用 PIL crop 即可；(3) 不要相信 Replicate README 上的 Python example，永远以 **该版本 ID 的 OpenAPI schema** 为准（虽然 firtoz/trellis 这个 README 也看不到精确 schema，所以只能实测）。
|
||||||
|
- **防御**: 接 Replicate 新模型前先用 1 美元额度做一次最小输入测试，打印 `output` 的原始 dict 结构 + 每个 key 的值类型；不要假设 README 的 example 与实际部署版本一致。`mesh_generator.py` 里已经做了"把 raw_output_keys 和每个字段的 None 警告都打印"的防御日志。
|
||||||
|
- **关联**: Replicate, firtoz/trellis, Mesh Pipeline, view_transform, Trellis, 3D 重建, schema, OpenAPI, mesh_generator.py
|
||||||
|
|
||||||
|
### [PF-20260420-1501] Windows uvicorn --reload 缺 watchfiles 退化为轮询，代码改动不被热重载
|
||||||
|
- **症状**: 代码已修好（git diff / Read 看源文件都是新版），但后端运行时行为仍是旧代码。具体表现：CL-20260420-1212 修好 Zero123++ 切图后（`cols=2/rows=3` + 自动纠错），前端再触发一次转视角，切出的 view 图仍是 213×480（= 640/3 × 960/2，旧的 `cols=3,rows=2` 逻辑），而独立用当前代码调用 `_split_grid_image` 能正确切出 320×320。进程启动时间 11:55，改动时间 12:12，观察时间 15:00，期间未 reload 过任何改动。
|
||||||
|
- **根因**: uvicorn `--reload` 在未安装 `watchfiles` 或 `watchdog` 时 fallback 到 `StatReload`（基于轮询）。Windows 文件系统事件语义本就弱，加上深层子目录（`app/services/`）+ 新建文件（`view_transform.py` 在仓库里是新增 untracked 文件），几个因素叠加让 StatReload 漏通知/响应极慢，表现为"启动后改什么代码都不会重载"。venv 里 `watchfiles` 和 `watchdog` 双双 MISSING 是核心证据。
|
||||||
|
- **解法**: (1) `pip install watchfiles==0.24.0`（uvicorn 官方首选 reloader）；(2) 写入 `requirements.txt` 和 `requirements-lock.txt`，避免其他设备重装环境时再次踩坑；(3) **kill 当前 uvicorn 进程重启一次**——新进程才会用上 WatchFiles reloader，并同步加载最新代码。仅装依赖不重启不会生效，因为当前进程已经加载了 StatReload。
|
||||||
|
- **防御**: Windows 上只要 uvicorn 带 `--reload`，`watchfiles` 就是硬依赖，不是可选项。启动后首屏日志如果看到 `WatchFiles detected changes` 或 `Started reloader process [xxx] using WatchFiles` 才算正常；如果只有 `Started reloader process [xxx] using StatReload` 就是退化状态。可以额外传 `--reload-dir app` 显式指定监控范围更保险。任何"改了代码不生效"的诡异现象，第一时间先确认进程是否已经重载（看日志里的文件变更提醒，或对比进程启动时间 vs 文件 mtime），再排查代码逻辑。
|
||||||
|
- **关联**: uvicorn, --reload, watchfiles, StatReload, FastAPI, Windows, 热重载, requirements.txt, view_transform.py, Zero123++
|
||||||
|
|
||||||
|
### [PF-20260420-1212] Zero123++ 输出 grid 布局被文档措辞"3×2"误导
|
||||||
|
- **症状**: Zero123++ 视角变换后切出的 6 张图严重错位，每张子图呈窄长条（宽:高 约 1:2），画面里上下拼着两个教堂，边缘大量留白。拼接图原图视觉正常。
|
||||||
|
- **根因**: Zero123++ 官方 README 写 "output is a 3×2 grid of 6 views"，但 `jd7h/zero123plusplus` 这个 Replicate 部署版本实际输出的是 **2 列 × 3 行**（高图，如 640×960），而 config.py 里按"3 列 × 2 行"配置了 `grid_layout`。切图时 `cell_w = 640//3 = 213, cell_h = 960//2 = 480`，每个切片横跨了真实 grid 中两行的一部分，于是每张图都拼着两个视角的局部。
|
||||||
|
- **解法**: (1) `config.py` 的 `VIEW_TRANSFORM_MODELS["zero123plus"].grid_layout` 改为 `{"cols": 2, "rows": 3}`；(2) `view_transform._split_grid_image` 加入"按实际图像长宽比 vs 配置 ratio 自动纠正"——假定每个单视角为正方形，真实 aspect ratio 应等于 `cols/rows`，若配置 ratio 与实际差异 >20% 就自动交换 cols/rows 并打 warning。
|
||||||
|
- **防御**: 任何涉及"grid 拼接图切分"的场景，不要完全相信模型文档的"A×B"措辞（A 是列还是行常有歧义），必须用**实际图像长宽比**做健壮性检查；最稳妥的做法是让 split 函数本身能根据单视角正方形假设自动推断布局，不信任硬编码。更激进的方案是直接用 PIL 探测内容块边界（但对有微量白边的模型不稳定）。
|
||||||
|
- **关联**: Zero123++, Replicate, jd7h/zero123plusplus, grid 切图, PIL, view_transform.py, config.py, Novel View Synthesis
|
||||||
|
|
||||||
### [PF-20260412-1530] Python load_dotenv 默认不覆盖已有环境变量 + 模块级变量在 import 时固化
|
### [PF-20260412-1530] Python load_dotenv 默认不覆盖已有环境变量 + 模块级变量在 import 时固化
|
||||||
- **症状**: 修改 .env 切换 API 供应商后，后端仍报旧供应商的错误（如 DeepSeek 报 "Model Not Exist"，实际发送的模型名是 OpenAI 的 gpt-4o-mini）
|
- **症状**: 修改 .env 切换 API 供应商后，后端仍报旧供应商的错误（如 DeepSeek 报 "Model Not Exist"，实际发送的模型名是 OpenAI 的 gpt-4o-mini）
|
||||||
- **根因**: 两层叠加：(1) `load_dotenv()` 默认 `override=False`，如果进程/系统中已有同名环境变量，.env 中的新值不会生效；(2) `config.py` 使用模块级常量 `LLM_MODEL = os.getenv(...)` 在 import 时就求值固化，而 `main.py` 的 import 链在 `load_dotenv()` 之前就触发了 config.py 的加载
|
- **根因**: 两层叠加：(1) `load_dotenv()` 默认 `override=False`，如果进程/系统中已有同名环境变量，.env 中的新值不会生效；(2) `config.py` 使用模块级常量 `LLM_MODEL = os.getenv(...)` 在 import 时就求值固化，而 `main.py` 的 import 链在 `load_dotenv()` 之前就触发了 config.py 的加载
|
||||||
|
|||||||
@@ -73,8 +73,33 @@ Agent 开始处理一个新任务时，判断是否需要读取近期详细记
|
|||||||
Agent 在即将输出最终回复前，**必须**逐项检查以下清单。
|
Agent 在即将输出最终回复前，**必须**逐项检查以下清单。
|
||||||
这是硬性要求，不是建议——**跳过任何一项都视为执行错误**。
|
这是硬性要求，不是建议——**跳过任何一项都视为执行错误**。
|
||||||
|
|
||||||
|
### 前置项（每次回复前无条件执行）
|
||||||
|
|
||||||
|
**A. 画像信号扫描（短路版）**
|
||||||
|
|
||||||
|
目的：以最小 token 成本维持 `profile-memory` Skill 的被动检测通路。
|
||||||
|
|
||||||
|
步骤：
|
||||||
|
|
||||||
|
1. **快判（词表匹配）**：扫描本次对话中**用户消息**，检查是否**明显**出现以下偏好/决策触发词族之一：
|
||||||
|
|
||||||
|
- 个人偏好信号：`我喜欢` / `我倾向` / `我不喜欢` / `我讨厌` / `以后都` / `以后别` /
|
||||||
|
`别再` / `不要再` / `我的风格` / `我的偏好` / `太花哨` / `minimal` /
|
||||||
|
`简洁` / `精炼` / `啰嗦`
|
||||||
|
- 项目决策信号：`这个项目是` / `目标用户是` / `技术栈` / `架构上` /
|
||||||
|
`产品方向` / `定位是`
|
||||||
|
|
||||||
|
2. **分支**：
|
||||||
|
- 无匹配 → **直接跳过**，进入下一 checklist 项（thinking 应在 50 token 内结束）
|
||||||
|
- 有匹配 → 读取 `.cursor/skills/profile-memory/SKILL.md` 并执行操作 A 的确认流程
|
||||||
|
|
||||||
|
3. **约束**：本项不做全量语义判断——漏记隐式信号是可接受的权衡。
|
||||||
|
用户如需记录隐式偏好可显式说"把这条记入画像"。
|
||||||
|
|
||||||
|
### 变更检查项（仅当本次有代码/配置文件改动时执行）
|
||||||
|
|
||||||
1. **本次是否有代码/配置文件改动？**（不含 `.cursor/` 下的基础设施文件）
|
1. **本次是否有代码/配置文件改动？**（不含 `.cursor/` 下的基础设施文件）
|
||||||
- 否 → 跳过后续项
|
- 否 → 跳过本组后续项，直接进入"收尾项"
|
||||||
- 是 → 继续
|
- 是 → 继续
|
||||||
|
|
||||||
2. **是否已写入三层开发日志？**
|
2. **是否已写入三层开发日志？**
|
||||||
@@ -89,9 +114,12 @@ Agent 在即将输出最终回复前，**必须**逐项检查以下清单。
|
|||||||
- 否 → 跳过
|
- 否 → 跳过
|
||||||
- 是 → 执行 `epee-orchestrator.mdc` 中的自迭代确认流程
|
- 是 → 执行 `epee-orchestrator.mdc` 中的自迭代确认流程
|
||||||
|
|
||||||
5. **静默 Hook 重复触发**（每次 checklist 完成后必须执行）
|
### 收尾项（每次回复前无条件执行）
|
||||||
|
|
||||||
|
**Z. 静默 Hook ack**
|
||||||
|
|
||||||
- 用 Write 工具创建空文件 `.cursor/changelog/.changelog-ack`
|
- 用 Write 工具创建空文件 `.cursor/changelog/.changelog-ack`
|
||||||
- 这会更新 ack 文件的 mtime，阻止 `check-changelog.ps1` hook 在后续回复中重复提醒
|
- 这会更新 ack 文件的 mtime，阻止 `check-changelog.ps1` hook 在后续回复中重复提醒
|
||||||
|
|
||||||
**执行原则**：先完成 checklist 中的所有写入动作，再输出面向用户的回复文本。
|
**执行原则**：先完成 checklist 中的所有写入动作，再输出面向用户的回复文本。
|
||||||
回复末尾如果执行了第 2 项，附 `[已记录到开发日志]`。
|
回复末尾如果执行了变更检查项第 2 项，附 `[已记录到开发日志]`。
|
||||||
|
|||||||
31
.cursor/rules/common/cursor-init-recall.mdc
Normal file
31
.cursor/rules/common/cursor-init-recall.mdc
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
---
|
||||||
|
description: 当用户要求初始化/重置 .cursor 目录（新项目首次落地模板）时，引导 Agent 读取 cursor-init Skill 并按其流程执行
|
||||||
|
globs:
|
||||||
|
alwaysApply: false
|
||||||
|
---
|
||||||
|
|
||||||
|
## .cursor 初始化触发
|
||||||
|
|
||||||
|
当用户表达以下意图之一时，读取并执行 `cursor-init` Skill：
|
||||||
|
|
||||||
|
**触发关键词**（匹配任意一条即可）：
|
||||||
|
|
||||||
|
- "初始化cursor" / "初始化 cursor" / "cursor 初始化"
|
||||||
|
- "重置 cursor" / "reset cursor"
|
||||||
|
- "cursor init" / "init cursor"
|
||||||
|
- "把复制过来的 .cursor 清理一下" / "按 baserule 归位一下"
|
||||||
|
|
||||||
|
**执行方式**：
|
||||||
|
|
||||||
|
1. 读取 `.cursor/skills/cursor-init/SKILL.md`
|
||||||
|
2. 严格按 Skill 中的 0 → 6 阶段流程执行
|
||||||
|
3. **稳定准确优先于 token 成本**：
|
||||||
|
- 破坏性操作（删除、重置、移动）前必须给用户 dry-run 清单
|
||||||
|
- 分类不清的文件必须逐条询问用户，不要猜
|
||||||
|
- 开始前先执行 `git status` 并提醒用户 commit/stash
|
||||||
|
4. 本 Skill 预期在新项目生命周期中只运行一次，但设计为幂等——重复运行在已干净状态下不应造成破坏
|
||||||
|
|
||||||
|
**不触发本 Skill 的情况**：
|
||||||
|
|
||||||
|
- 用户只是问"cursor 有什么 skill"——这是浏览需求，走 `epee-orchestrator` 的操作 A
|
||||||
|
- 用户只是想初始化某个具体数据文件（比如"初始化画像"）——这是对应 Skill 自己的流程（如 `profile-memory`），不涉及全局结构重置
|
||||||
@@ -34,8 +34,13 @@ alwaysApply: true
|
|||||||
3. 用 Read 工具读取该行号 ±15 行范围，获取原始上下文和来源信息
|
3. 用 Read 工具读取该行号 ±15 行范围，获取原始上下文和来源信息
|
||||||
4. 一次上溯通常只涉及 1-2 条记录，不批量上溯
|
4. 一次上溯通常只涉及 1-2 条记录，不批量上溯
|
||||||
|
|
||||||
## 被动检测提醒
|
## 被动检测触发点
|
||||||
|
|
||||||
Agent 在整个对话过程中应保持对画像信号的被动感知。
|
被动检测不在本 Rule 执行，而是由 `changelog-recall.mdc` 的
|
||||||
当对话结束、用户的主线任务完成后，如果检测到了新的画像信息，
|
**任务完成 Checklist 前置项 A（画像信号扫描）** 统一触发。
|
||||||
应读取 `profile-memory` Skill 并执行其"操作 A"的确认流程。
|
|
||||||
|
理由：本 Rule 仅负责上下文注入（低成本、每次必做）；被动检测需要挂入
|
||||||
|
已有强制力的 checklist 中才能避免被 Agent 遗漏，该 checklist 由
|
||||||
|
`changelog-recall` 维护，两者分工清晰。
|
||||||
|
|
||||||
|
具体触发词族和短路逻辑详见 `changelog-recall.mdc` 中的前置项 A 定义。
|
||||||
|
|||||||
412
.cursor/skills/cursor-init/SKILL.md
Normal file
412
.cursor/skills/cursor-init/SKILL.md
Normal file
@@ -0,0 +1,412 @@
|
|||||||
|
---
|
||||||
|
name: cursor-init
|
||||||
|
description: >-
|
||||||
|
初始化新项目的 .cursor 结构。当用户把本项目的 .cursor 模板复制到新项目后说
|
||||||
|
"初始化cursor"、"cursor 初始化"、"重置 cursor"、"cursor init" 时触发。
|
||||||
|
按 baserule.mdc 约定识别并迁移目标项目原有的 rules/skills，清理模板中残留的
|
||||||
|
项目专用数据（changelog/deferred/pitfalls/profile/distillery/local-env/
|
||||||
|
项目级 rules 与 skills 等），把 .cursor 重置为可以直接投入新项目的干净起点。
|
||||||
|
该 Skill 通常每个新项目只运行一次，以稳定准确为首要目标。
|
||||||
|
---
|
||||||
|
|
||||||
|
# Cursor Init Skill
|
||||||
|
|
||||||
|
把从其它项目复制过来的 `.cursor/` 目录重置为当前新项目的干净起点。
|
||||||
|
|
||||||
|
## 使用场景
|
||||||
|
|
||||||
|
典型流程：
|
||||||
|
|
||||||
|
```
|
||||||
|
1. 用户在 "源项目 A" 中使用本 .cursor 模板开发
|
||||||
|
2. 用户开 "新项目 B"，把 A 的 .cursor/ 整体拷贝到 B 的根目录
|
||||||
|
3. B 原先可能也有自己零散的 rules/SKILL 文件（路径、命名未必标准）
|
||||||
|
4. 用户在 B 中说"初始化cursor"
|
||||||
|
5. 本 Skill 接管：
|
||||||
|
- 把 B 原有的 rules/skills 按 baserule.mdc 归位
|
||||||
|
- 把 A 遗留的项目专用数据清空或删除
|
||||||
|
- 重建干净的 registry，让 B 从第一天起就有规范的 .cursor
|
||||||
|
```
|
||||||
|
|
||||||
|
## 触发条件
|
||||||
|
|
||||||
|
用户直接表达"初始化 cursor"类意图：
|
||||||
|
|
||||||
|
- `初始化cursor` / `初始化 cursor` / `cursor 初始化`
|
||||||
|
- `重置 cursor` / `reset cursor`
|
||||||
|
- `cursor init` / `init cursor`
|
||||||
|
- 口头描述"把复制过来的 .cursor 清理一下"、"按 baserule 归位一下"
|
||||||
|
|
||||||
|
## 执行原则（不可协商）
|
||||||
|
|
||||||
|
1. **稳定准确 > token 成本**：每一步可以多读、多确认、让用户点头，不要图快
|
||||||
|
2. **破坏性操作必须 dry-run**：删除、重置必须先列清单给用户确认
|
||||||
|
3. **不可逆操作前提醒 git**：开始前先提示用户确认工作区已 commit/stash，便于回滚
|
||||||
|
4. **模糊就问**：分类不清的文件一律问用户，不要猜
|
||||||
|
5. **幂等**：反复运行应当无害（第二次不会再改已经干净的 .cursor）
|
||||||
|
|
||||||
|
## 核心流程
|
||||||
|
|
||||||
|
### 阶段 0：前置确认
|
||||||
|
|
||||||
|
```
|
||||||
|
1. 检查当前工作目录下存在 .cursor/
|
||||||
|
- 不存在 → 直接结束，提示用户先复制模板
|
||||||
|
2. 运行 `git status`，若有未提交改动：
|
||||||
|
- 提醒用户："建议先 commit 或 stash，便于回滚"
|
||||||
|
- 等用户明确回复"继续"再往下
|
||||||
|
3. 向用户声明本次操作的范围（见"分组规则"），请求用户口头确认启动
|
||||||
|
```
|
||||||
|
|
||||||
|
### 阶段 1：递归扫描 `.cursor/`
|
||||||
|
|
||||||
|
```
|
||||||
|
1. 用 shell 列出 .cursor 下所有文件（含子目录）
|
||||||
|
2. 把每个文件对照"规范清单"和"清理清单"分成三组：
|
||||||
|
- A 组（canonical）：在规范清单中，原样保留
|
||||||
|
- B 组（template-data）：在清理清单中，需要删除或重置
|
||||||
|
- C 组（foreign）：两张清单都没覆盖到的，视作目标项目原有文件或未知项
|
||||||
|
3. 把分组结果用表格汇报给用户：
|
||||||
|
| 组 | 路径 | 处理动作 |
|
||||||
|
```
|
||||||
|
|
||||||
|
### 阶段 2：处理 C 组（目标项目原有文件归位）
|
||||||
|
|
||||||
|
对 C 组中的每个文件，按 baserule.mdc 的归属约定分类，逐条询问用户（可一次性列清单批量确认）：
|
||||||
|
|
||||||
|
| 文件特征 | 建议归属 | 目标路径 |
|
||||||
|
|----------|----------|----------|
|
||||||
|
| `.mdc` 且内容是跨项目通用规则 | 通用 Rule | `.cursor/rules/common/<name>.mdc` |
|
||||||
|
| `.mdc` 且内容是当前新项目专属规则 | 项目 Rule | `.cursor/rules/project/<name>.mdc` |
|
||||||
|
| 包含 `SKILL.md` 的目录 | Skill（无论通用/项目专属） | `.cursor/skills/<skill-name>/` |
|
||||||
|
| 看不出归属 | 询问用户 | — |
|
||||||
|
| 明显是临时/垃圾文件（`*.log`、`*.tmp`、缓存等） | 删除（需用户确认） | — |
|
||||||
|
|
||||||
|
执行要点：
|
||||||
|
|
||||||
|
- **先列清单一次性确认**，然后批量执行移动/删除，避免交互过于频繁
|
||||||
|
- **重名冲突**：C 组文件若与 A 组规范文件重名（例如 C 组有 `baserule.mdc`），**保留 A 组版本**，把 C 组备份到 `.cursor/_init-backup/` 下让用户自行 diff，不直接覆盖
|
||||||
|
- **Skill 归属提示**：通用 Skill 建议用户之后手动同步到 `~/.cursor/skills/`（跨项目便利副本，可选）
|
||||||
|
- **迁移后核查**：移动完成后重新扫描，确认 C 组已清空
|
||||||
|
|
||||||
|
### 阶段 3：处理 B 组（源项目项目专用数据清理/重置）
|
||||||
|
|
||||||
|
按"清理清单"执行：
|
||||||
|
|
||||||
|
**A. 直接删除**
|
||||||
|
|
||||||
|
- `.cursor/rules/project/*.mdc`（全部）—— 源项目的项目级 rules，新项目不适用
|
||||||
|
- `.cursor/skills/<非规范 skill 目录>/`—— 源项目的项目级 Skills（不在规范 Skill 列表中的所有 Skill 目录）
|
||||||
|
- `.cursor/plans/` 下所有文件（目录保留，内容清空）
|
||||||
|
- `.cursor/debug-*.log`、`.cursor/*.log` —— 调试日志
|
||||||
|
- `.cursor/local-env.json` —— 设备绑定，需要新设备重新生成（`local-env-check.mdc` 会自动探测）
|
||||||
|
|
||||||
|
**B. 重置为空模板**（保留文件，仅清内容）
|
||||||
|
|
||||||
|
| 文件 | 模板（见"模板内容"节） |
|
||||||
|
|------|------------------------|
|
||||||
|
| `.cursor/changelog/changelog-full.md` | L1 模板 |
|
||||||
|
| `.cursor/changelog/changelog-recent.md` | L2 模板 |
|
||||||
|
| `.cursor/changelog/changelog-headlines.md` | L3 模板 |
|
||||||
|
| `.cursor/changelog/.changelog-ack` | 空文件（touch） |
|
||||||
|
| `.cursor/deferred/registry.md` | deferred 模板 |
|
||||||
|
| `.cursor/pitfalls/pitfalls.md` | pitfalls 模板 |
|
||||||
|
| `.cursor/distillery/problems.md` | problems 模板 |
|
||||||
|
| `.cursor/distillery/insights.md` | insights 模板 |
|
||||||
|
| `.cursor/distillery/golden-rules.md` | golden-rules 模板 |
|
||||||
|
| `.cursor/profile/project-profile.md` | project-profile 模板 |
|
||||||
|
| `.cursor/profile/project-profile-log.md` | project-profile-log 模板 |
|
||||||
|
|
||||||
|
执行要点：
|
||||||
|
|
||||||
|
- 每个重置动作前**先 Read 现有内容预览前 10 行**给用户，避免误删有价值的数据（特别是 deferred/pitfalls 用户可能想保留）
|
||||||
|
- 如用户对某个数据文件明确说"保留"（例如 golden-rules 想带过去），跳过该文件的重置
|
||||||
|
|
||||||
|
### 阶段 4：重建 registry
|
||||||
|
|
||||||
|
打开 `.cursor/skills/epee-orchestrator/registry.md`：
|
||||||
|
|
||||||
|
1. 解析现有条目（每条 `### <skill-name>` 块）
|
||||||
|
2. 删除所有 `类型: 项目级` 的条目
|
||||||
|
3. 遍历 `.cursor/skills/` 目录，对照 registry：
|
||||||
|
- registry 有条目但 skill 目录不存在 → 删除条目（说明是被第 3 阶段清理掉的项目级 skill）
|
||||||
|
- skill 目录存在但 registry 无条目 → 读取该 skill 的 SKILL.md frontmatter，新增条目
|
||||||
|
4. **确保 `cursor-init` 条目本身存在**（类型: 基础设施）
|
||||||
|
5. 写回 registry.md
|
||||||
|
|
||||||
|
### 阶段 5：同步 `hooks.json`（跨平台保守处理）
|
||||||
|
|
||||||
|
- 读取 `.cursor/hooks.json`
|
||||||
|
- 若 `command` 字段硬编码为 `powershell ...`，且目标新项目声明/探测到的 shell 不是 powershell（参考 `local-env-check.mdc`），**提醒用户**需要按 `hooks/README.md` 的说明手动改成 `bash .cursor/hooks/xxx.sh`
|
||||||
|
- 本阶段不自动改 hooks.json，避免误判
|
||||||
|
|
||||||
|
### 阶段 6：验证与报告
|
||||||
|
|
||||||
|
```
|
||||||
|
1. 重新递归扫描 .cursor/，再次分组
|
||||||
|
2. 期望状态：
|
||||||
|
- A 组：全部保留，文件内容未被动过
|
||||||
|
- B 组：数据文件仅含模板内容；项目级 rules/skills/日志 已删除
|
||||||
|
- C 组：为空（或仅剩用户明确要求保留的文件）
|
||||||
|
3. 给用户一份结构化报告，至少包含：
|
||||||
|
- 移动的文件（from → to）
|
||||||
|
- 删除的文件
|
||||||
|
- 重置的文件
|
||||||
|
- 新注册/移除的 registry 条目
|
||||||
|
- 未处理的文件（如果有，逐条说明原因）
|
||||||
|
4. 收尾提示：
|
||||||
|
> 初始化完成。建议现在执行：
|
||||||
|
> git add .cursor/
|
||||||
|
> git diff --cached -- .cursor/
|
||||||
|
> git commit -m "chore(cursor): initialize .cursor from template"
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 规范清单（canonical）
|
||||||
|
|
||||||
|
下列文件构成本 `.cursor` 模板的"主干"，初始化后必须都在、内容不被删改（数据文件除外，见"清理清单"）：
|
||||||
|
|
||||||
|
### 顶层
|
||||||
|
|
||||||
|
- `.cursor/hooks.json`
|
||||||
|
- `.cursor/local-env.example.json`
|
||||||
|
|
||||||
|
### Rules（通用）
|
||||||
|
|
||||||
|
- `.cursor/rules/common/baserule.mdc`
|
||||||
|
- `.cursor/rules/common/changelog-recall.mdc`
|
||||||
|
- `.cursor/rules/common/deferred-recall.mdc`
|
||||||
|
- `.cursor/rules/common/distillery-recall.mdc`
|
||||||
|
- `.cursor/rules/common/epee-orchestrator.mdc`
|
||||||
|
- `.cursor/rules/common/pitfall-recall.mdc`
|
||||||
|
- `.cursor/rules/common/profile-recall.mdc`
|
||||||
|
- `.cursor/rules/common/cursor-init-recall.mdc`
|
||||||
|
|
||||||
|
### Rules（项目专属目录）
|
||||||
|
|
||||||
|
- `.cursor/rules/project/`（保留**空目录**；源项目的 `.mdc` 内容一律删除）
|
||||||
|
|
||||||
|
### Skills（规范 Skill 目录白名单）
|
||||||
|
|
||||||
|
- `.cursor/skills/cursor-init/`
|
||||||
|
- `.cursor/skills/deferred-decisions/`
|
||||||
|
- `.cursor/skills/dev-changelog/`
|
||||||
|
- `.cursor/skills/epee-orchestrator/`（含 `registry.md`，见阶段 4）
|
||||||
|
- `.cursor/skills/pitfall-journal/`
|
||||||
|
- `.cursor/skills/problem-distillery/`
|
||||||
|
- `.cursor/skills/profile-memory/`
|
||||||
|
|
||||||
|
> **任何不在此白名单中的 skill 目录**，在阶段 3 中一律删除（视为源项目的项目级 Skill）。
|
||||||
|
|
||||||
|
### Hooks
|
||||||
|
|
||||||
|
- `.cursor/hooks/README.md`
|
||||||
|
- `.cursor/hooks/run-hook.ps1`
|
||||||
|
- `.cursor/hooks/session-init.ps1`
|
||||||
|
- `.cursor/hooks/session-init.sh`
|
||||||
|
- `.cursor/hooks/check-changelog.ps1`
|
||||||
|
- `.cursor/hooks/check-changelog.sh`
|
||||||
|
|
||||||
|
### 数据占位目录（保留目录，文件重置为模板内容）
|
||||||
|
|
||||||
|
- `.cursor/changelog/{changelog-full.md, changelog-recent.md, changelog-headlines.md, .changelog-ack}`
|
||||||
|
- `.cursor/deferred/registry.md`
|
||||||
|
- `.cursor/pitfalls/pitfalls.md`
|
||||||
|
- `.cursor/distillery/{problems.md, insights.md, golden-rules.md}`
|
||||||
|
- `.cursor/profile/{project-profile.md, project-profile-log.md}`
|
||||||
|
- `.cursor/plans/`（空目录）
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 清理清单（cleanup list）
|
||||||
|
|
||||||
|
### 强制删除
|
||||||
|
|
||||||
|
| 路径 | 原因 |
|
||||||
|
|------|------|
|
||||||
|
| `.cursor/rules/project/*.mdc` | 源项目的项目级 Rules |
|
||||||
|
| `.cursor/skills/<非白名单>/` | 源项目的项目级 Skills |
|
||||||
|
| `.cursor/plans/*`（内容） | 源项目规划文档 |
|
||||||
|
| `.cursor/*.log`、`.cursor/debug-*.log` | 调试日志遗留 |
|
||||||
|
| `.cursor/local-env.json` | 设备绑定配置，需由新设备重新生成 |
|
||||||
|
| `.cursor/_init-backup/`（如果是上一轮残留） | 仅阶段 2 冲突备份用，运行前应不存在 |
|
||||||
|
|
||||||
|
### 重置为模板
|
||||||
|
|
||||||
|
见"模板内容"节。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 模板内容
|
||||||
|
|
||||||
|
重置数据文件时使用以下内容。带 `{{DATE}}` 的占位符替换为当天日期（`YYYY-MM-DD`）。
|
||||||
|
|
||||||
|
### changelog-full.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Dev Changelog — Full
|
||||||
|
|
||||||
|
完整的开发改动记录，按时间倒序排列。作为主动 RAG 的数据源，用户手动唤醒时读取。
|
||||||
|
|
||||||
|
## 记录
|
||||||
|
```
|
||||||
|
|
||||||
|
### changelog-recent.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Dev Changelog — Recent
|
||||||
|
|
||||||
|
最近 ~10 次改动的摘要记录，按时间倒序排列。
|
||||||
|
当 Agent 检测到当前任务与近期改动相关时自动读取。
|
||||||
|
```
|
||||||
|
|
||||||
|
### changelog-headlines.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Dev Changelog — Headlines
|
||||||
|
|
||||||
|
最近 ~50 次改动的一句话概要，按时间倒序排列。每次会话自动注入上下文。
|
||||||
|
```
|
||||||
|
|
||||||
|
### .changelog-ack
|
||||||
|
|
||||||
|
空文件（0 字节），只用于更新 mtime 阻止 hook 重复提醒。
|
||||||
|
|
||||||
|
### deferred/registry.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Deferred Decisions Registry
|
||||||
|
|
||||||
|
## Active Items
|
||||||
|
|
||||||
|
（暂无延期方案）
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Completed / Cancelled Items
|
||||||
|
|
||||||
|
（暂无已完成或已废弃的方案）
|
||||||
|
```
|
||||||
|
|
||||||
|
### pitfalls/pitfalls.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Pitfall Journal
|
||||||
|
|
||||||
|
开发过程中踩过的坑，按时间倒序排列。
|
||||||
|
Agent 进入 Debug mode 或遇到运行时错误时自动检索匹配。
|
||||||
|
|
||||||
|
---
|
||||||
|
```
|
||||||
|
|
||||||
|
### distillery/problems.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Problem Distillery — Problems
|
||||||
|
|
||||||
|
反复出现的顽固问题追踪记录，按时间倒序排列。
|
||||||
|
|
||||||
|
<!-- 新条目追加在此行下方 -->
|
||||||
|
```
|
||||||
|
|
||||||
|
### distillery/insights.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Problem Distillery — Insights
|
||||||
|
|
||||||
|
从已解决的顽固问题中蒸馏出的精炼方法论。
|
||||||
|
|
||||||
|
<!-- 新条目追加在此行下方 -->
|
||||||
|
|
||||||
|
---
|
||||||
|
last_distill_date: {{DATE}}
|
||||||
|
```
|
||||||
|
|
||||||
|
### distillery/golden-rules.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Golden Rules
|
||||||
|
|
||||||
|
经过实践验证（权重 >= 5）的精炼认知，每次新会话自动注入。
|
||||||
|
|
||||||
|
<!-- 当条目达到权重阈值后由 Agent 自动写入 -->
|
||||||
|
```
|
||||||
|
|
||||||
|
### profile/project-profile.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Project Profile
|
||||||
|
|
||||||
|
## 项目定位
|
||||||
|
|
||||||
|
## 技术栈与架构
|
||||||
|
|
||||||
|
## 设计约定
|
||||||
|
|
||||||
|
## 产品方向
|
||||||
|
```
|
||||||
|
|
||||||
|
### profile/project-profile-log.md
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
# Project Profile Log
|
||||||
|
|
||||||
|
详细记录每次项目画像更新的完整上下文，按时间正序追加。
|
||||||
|
|
||||||
|
## 记录
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 冲突与边界情况处理
|
||||||
|
|
||||||
|
| 场景 | 处理 |
|
||||||
|
|------|------|
|
||||||
|
| C 组某文件与 A 组重名 | 保留 A 组；C 组移到 `.cursor/_init-backup/`，告知用户自行 diff |
|
||||||
|
| C 组有 `SKILL.md` 且 skill 名与 A 组白名单同名 | 保留 A 组 skill；C 组整个 skill 目录移到 `_init-backup/` |
|
||||||
|
| 数据文件（如 `pitfalls.md`）用户明确说"保留" | 跳过该文件重置 |
|
||||||
|
| `local-env.json` 存在且用户说"我就在这台机器上开 B，保留它" | 跳过删除，但提醒用户其已在 `.gitignore` |
|
||||||
|
| `.cursor/rules/project/` 为空目录 | 保留空目录（便于未来放项目级 rules） |
|
||||||
|
| 扫描到 `.cursor/_init-backup/`（上轮残留） | 警告用户并询问：删除 / 保留 / 重命名 |
|
||||||
|
| `git status` 不能执行（不是 git 仓库） | 警告但不阻塞，改为建议用户手动备份 |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 与其他系统的协作
|
||||||
|
|
||||||
|
| 系统 | 关系 | 说明 |
|
||||||
|
|------|------|------|
|
||||||
|
| `baserule.mdc` | 分类权威 | 阶段 2 归位目录严格按 baserule 约定 |
|
||||||
|
| `epee-orchestrator` Skill | 双向 | 本 Skill 被 Orchestrator 在 registry 里注册；同时本 Skill 负责清理 registry |
|
||||||
|
| `dev-changelog` / `pitfall-journal` / `deferred-decisions` / `problem-distillery` / `profile-memory` | 下游数据主人 | 本 Skill 只在阶段 3 重置其数据文件，不改动 SKILL.md |
|
||||||
|
| `local-env-check.mdc` | 后继 | 本 Skill 删除 `local-env.json`，后续新会话由 `local-env-check` 自动重新探测并生成 |
|
||||||
|
| `cursor-init-recall.mdc` | 触发器 | 负责匹配"初始化cursor"等关键词，引导 Agent 读取本 SKILL.md |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 一次运行的最终状态（验收标准）
|
||||||
|
|
||||||
|
运行结束后 `.cursor/` 应当满足：
|
||||||
|
|
||||||
|
1. 规范清单中列出的所有文件/目录都存在
|
||||||
|
2. 所有数据文件（changelog/deferred/pitfalls/distillery/profile）仅含模板内容
|
||||||
|
3. `.cursor/rules/project/` 为空目录
|
||||||
|
4. `.cursor/skills/` 下仅有白名单中的 skill 目录
|
||||||
|
5. `.cursor/skills/epee-orchestrator/registry.md` 中只有：基础设施 + 个人级 skill 条目，且包含 `cursor-init` 条目
|
||||||
|
6. 不存在 `*.log`、`local-env.json`、`_init-backup/`（或 backup 已被用户确认保留/清理）
|
||||||
|
7. `git status .cursor/` 能让用户清楚看到所有改动
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 自迭代日志
|
||||||
|
|
||||||
|
本节记录使用本 Skill 过程中发现的必要检查项。
|
||||||
|
|
||||||
|
### 已知必要检查
|
||||||
|
|
||||||
|
1. **阶段 2 的 C 组归位前必须先做 dry-run 展示** —— 批量移动 .mdc / SKILL 文件是高破坏性操作，只要有一条分类错误就会污染 canonical 结构，必须让用户在列表上逐条过一遍再执行。
|
||||||
|
|
||||||
|
2. **重名冲突不许直接覆盖** —— C 组与 A 组重名时，A 组（模板版本）永远是 source of truth，冲突文件只能进 `_init-backup/`，让用户自行决定是否把差异合并回 common rule。
|
||||||
|
|
||||||
|
3. **registry 重建时先读后写** —— 阶段 4 不要直接用硬编码模板覆盖 registry.md，必须先解析现有条目，只移除项目级条目、补齐缺失条目，避免丢失用户自己添加的个人级 Skill 条目。
|
||||||
@@ -249,3 +249,11 @@ Agent 完成了一个涉及**代码或配置文件实质性改动**的任务后
|
|||||||
1. **大任务收尾遗漏风险** — 当单次任务涉及 5+ 个文件改动时，Agent 容易在输出总结回复后遗漏被动写入流程。应在生成最终回复前，先执行 `changelog-recall.mdc` 中的"任务完成 Checklist"，确认三层日志已写入后再输出回复。绝不能"先回复再补写"。
|
1. **大任务收尾遗漏风险** — 当单次任务涉及 5+ 个文件改动时，Agent 容易在输出总结回复后遗漏被动写入流程。应在生成最终回复前，先执行 `changelog-recall.mdc` 中的"任务完成 Checklist"，确认三层日志已写入后再输出回复。绝不能"先回复再补写"。
|
||||||
|
|
||||||
2. **L3/L2 滚动窗口必须落地** — 操作 A 第 4 步不是「插入即结束」：写入后必须数清条目（L3 为以 `- [` 开头的列表行，L2 为 `### [CL-` 标题行）。L3 超过 50 条、L2 超过 20 条时，必须从**文件底部（最旧）**整段删除条目直至恰好满足上限；禁止长期只追加不修剪。若发现 `changelog-headlines.md` 列表行多于 50，说明上次写入未执行本项，本次补修剪并自检。
|
2. **L3/L2 滚动窗口必须落地** — 操作 A 第 4 步不是「插入即结束」：写入后必须数清条目（L3 为以 `- [` 开头的列表行，L2 为 `### [CL-` 标题行）。L3 超过 50 条、L2 超过 20 条时，必须从**文件底部（最旧）**整段删除条目直至恰好满足上限；禁止长期只追加不修剪。若发现 `changelog-headlines.md` 列表行多于 50，说明上次写入未执行本项，本次补修剪并自检。
|
||||||
|
|
||||||
|
3. **顶部插入 StrReplace 范式（L1/L2）** — L1 和 L2 的每个条目都是多行结构（标题 + 多条 `- **字段**:`）。使用 StrReplace 在顶部插入新条目时，anchor（`old_string`）有且仅有两种合法选择：
|
||||||
|
(a) 只包含新条目之前的"稳定前缀"（如 L1 的 `## 记录\n\n` 或 L2 的整段文件头说明），**不触及任何已有条目的任何一行**；`new_string` = 稳定前缀 + 新条目完整内容 + 空行。
|
||||||
|
(b) 把旧首条目的**完整多行内容**（标题行 + 全部字段行）都纳入 `old_string`；`new_string` = 新条目完整内容 + 空行 + 旧首条目完整内容。
|
||||||
|
|
||||||
|
**绝对禁止**：只把旧首条目的标题行（或前 1-2 字段）当 anchor 而不带上剩余字段行——StrReplace 会吞掉这些 anchor 行但不动剩余字段，造成"旧标题丢失、字段游离"的半损坏状态（2026-04-20 在 `pitfall-journal` 的写入中已实际踩过此坑）。
|
||||||
|
|
||||||
|
**写入后自检**：Read 文件头部 30 行，确认看到新条目完整 + 旧首条目标题行仍存在且字段完整跟随。L3 的一行条目不受本条约束（它就是单行，天然无此风险）。
|
||||||
|
|||||||
@@ -17,6 +17,14 @@
|
|||||||
|
|
||||||
## 已注册 Skill
|
## 已注册 Skill
|
||||||
|
|
||||||
|
### cursor-init
|
||||||
|
- **类型**: 基础设施
|
||||||
|
- **能力**: 把从其它项目复制过来的 .cursor/ 重置为新项目的干净起点——按 baserule 归位目标项目原有的 rules/skills，清理源项目的项目专用数据，重建干净的 registry
|
||||||
|
- **触发场景**: "初始化cursor"、"cursor 初始化"、"重置 cursor"、"cursor init"、"init cursor"、"reset cursor"、"按 baserule 归位"、新项目首次落地 .cursor 模板
|
||||||
|
- **输出**: 重置/清理后的 `.cursor/` 结构（规范清单完整、项目级内容已清、数据文件为模板、registry 仅含通用条目）
|
||||||
|
- **路径**: .cursor/skills/cursor-init/SKILL.md
|
||||||
|
- **备注**: 每个新项目一次性运行，破坏性操作必须 dry-run；由 `cursor-init-recall.mdc` 触发；设计为幂等，重复运行无害
|
||||||
|
|
||||||
### deferred-decisions
|
### deferred-decisions
|
||||||
- **类型**: 基础设施
|
- **类型**: 基础设施
|
||||||
- **能力**: 记录和追踪延期的技术方案/决策，在关联任务出现时主动提醒
|
- **能力**: 记录和追踪延期的技术方案/决策，在关联任务出现时主动提醒
|
||||||
@@ -28,10 +36,10 @@
|
|||||||
### profile-memory
|
### profile-memory
|
||||||
- **类型**: 个人级
|
- **类型**: 个人级
|
||||||
- **能力**: 在对话中被动检测用户个人特质和项目信息，经确认后持久化为精简画像和详细日志
|
- **能力**: 在对话中被动检测用户个人特质和项目信息，经确认后持久化为精简画像和详细日志
|
||||||
- **触发场景**: "画像"、"profile"、"我的偏好"、"查看画像"、"项目信息"、"查看项目画像"、用户主动管理画像
|
- **触发场景**: "画像"、"profile"、"我的偏好"、"查看画像"、"项目信息"、"查看项目画像"、用户主动管理画像；被动检测由 `changelog-recall` checklist 前置项 A 的短路扫描触发（命中偏好/项目决策触发词族时）
|
||||||
- **输出**: ~/.cursor/profile/user-profile.md、.cursor/profile/project-profile.md 及对应 log 文件
|
- **输出**: ~/.cursor/profile/user-profile.md、.cursor/profile/project-profile.md 及对应 log 文件
|
||||||
- **路径**: .cursor/skills/profile-memory/SKILL.md
|
- **路径**: .cursor/skills/profile-memory/SKILL.md
|
||||||
- **备注**: 被动检测由 profile-recall Rule 触发；精简 Profile 每次会话自动注入上下文
|
- **备注**: 精简 Profile 每次会话由 `profile-recall` Rule 自动注入上下文；被动检测路径由 `changelog-recall` 的强制 checklist 前置项 A 兜底（2026-04-20 升级：原 `profile-recall` 的软性"被动检测提醒"失效率高，改为词表短路扫描挂入 checklist）
|
||||||
|
|
||||||
### dev-changelog
|
### dev-changelog
|
||||||
- **类型**: 基础设施
|
- **类型**: 基础设施
|
||||||
@@ -39,7 +47,7 @@
|
|||||||
- **触发场景**: "开发日志"、"changelog"、"最近改了什么"、"回顾改动"、"查看开发记录"、代码改动后自动写入
|
- **触发场景**: "开发日志"、"changelog"、"最近改了什么"、"回顾改动"、"查看开发记录"、代码改动后自动写入
|
||||||
- **输出**: .cursor/changelog/ 下的 changelog-full.md、changelog-recent.md、changelog-headlines.md
|
- **输出**: .cursor/changelog/ 下的 changelog-full.md、changelog-recent.md、changelog-headlines.md
|
||||||
- **路径**: .cursor/skills/dev-changelog/SKILL.md
|
- **路径**: .cursor/skills/dev-changelog/SKILL.md
|
||||||
- **备注**: 写入由 changelog-recall Rule 的"任务完成 Checklist"触发（原被动写入提醒已升级为强制 checklist）；L3 概要每次会话自动注入上下文；stop Hook 双保险兜底；写入后须维护 L3≤50 / L2≤20 滚动窗口（见 Skill 自迭代检查项）
|
- **备注**: 写入由 changelog-recall Rule 的"任务完成 Checklist"触发（原被动写入提醒已升级为强制 checklist）；L3 概要每次会话自动注入上下文；stop Hook 双保险兜底；写入后须维护 L3≤50 / L2≤20 滚动窗口，L1/L2 多行条目须遵循"顶部插入 StrReplace 范式"防止旧首条目被截断（见 Skill 自迭代检查项）
|
||||||
|
|
||||||
### pitfall-journal
|
### pitfall-journal
|
||||||
- **类型**: 基础设施
|
- **类型**: 基础设施
|
||||||
@@ -47,7 +55,7 @@
|
|||||||
- **触发场景**: debug 完成后、"踩坑"、"之前遇到过"、"坑"、进入 Debug mode、同类错误反复出现
|
- **触发场景**: debug 完成后、"踩坑"、"之前遇到过"、"坑"、进入 Debug mode、同类错误反复出现
|
||||||
- **输出**: .cursor/pitfalls/pitfalls.md 条目
|
- **输出**: .cursor/pitfalls/pitfalls.md 条目
|
||||||
- **路径**: .cursor/skills/pitfall-journal/SKILL.md
|
- **路径**: .cursor/skills/pitfall-journal/SKILL.md
|
||||||
- **备注**: 与 dev-changelog 互补——changelog 记事实，pitfall 记经验；由 pitfall-recall Rule 触发自动检索
|
- **备注**: 与 dev-changelog 互补——changelog 记事实，pitfall 记经验；由 pitfall-recall Rule 触发自动检索；写入时须遵循"顶部插入 StrReplace 范式"防止旧首条目标题丢失（见 Skill 自迭代检查项）
|
||||||
|
|
||||||
### problem-distillery
|
### problem-distillery
|
||||||
- **类型**: 基础设施
|
- **类型**: 基础设施
|
||||||
|
|||||||
@@ -113,4 +113,10 @@ description: >-
|
|||||||
|
|
||||||
### 已知必要检查
|
### 已知必要检查
|
||||||
|
|
||||||
（暂无）
|
1. **顶部插入必须保持旧首条目完整性** — 使用 StrReplace 在文件顶部插入新条目时（操作 A 第 4 步），anchor（`old_string`）有且仅有两种合法选择：
|
||||||
|
(a) 只包含新条目之前的"稳定前缀"（如 `---\n\n` 或整个文件头部说明段），**不触及任何已有条目的任何一行**；然后 `new_string` = 稳定前缀 + 新条目完整内容 + 空行。
|
||||||
|
(b) 把旧首条目的**完整多行内容**（标题行 + 全部字段行）都纳入 `old_string`；然后 `new_string` = 新条目完整内容 + 空行 + 旧首条目完整内容。
|
||||||
|
|
||||||
|
**绝对禁止**：把旧首条目的"标题行"单独当 anchor 而不带上它紧跟的字段行——StrReplace 是精确替换，这样做会删掉标题、让字段"无主"残留在新条目之后，造成半损坏状态（2026-04-20 实际踩过此坑）。
|
||||||
|
|
||||||
|
**写入后自检**：Read 文件头 25 行，确认看到 `### [PF-新ID]` 后紧跟其 5 字段，再往下能看到 `### [PF-旧首条目ID]` 标题行且字段完整跟随。
|
||||||
|
|||||||
@@ -1,9 +1,11 @@
|
|||||||
---
|
---
|
||||||
name: profile-memory
|
name: profile-memory
|
||||||
description: >-
|
description: >-
|
||||||
渐进式用户/项目画像系统。在对话中被动检测用户个人特质（审美、技术偏好、做事风格等）
|
渐进式用户/项目画像系统。两条触发路径：
|
||||||
和项目信息（定位、技术栈、产品方向等），对话结束前统一总结并经用户确认后记录。
|
（1）被动检测（主路径）——由 `changelog-recall` checklist 前置项 A 触发短路扫描，
|
||||||
当用户提到"画像"、"profile"、"我的偏好"、"查看画像"、"项目信息"等时触发。
|
命中偏好/项目决策触发词时执行操作 A（总结 + 用户确认 + 写入）。
|
||||||
|
（2）显式管理——当用户提到"画像"、"profile"、"查看画像"、"我的偏好"、"项目信息"等时
|
||||||
|
执行操作 B（浏览、修改、删除已有条目）。
|
||||||
---
|
---
|
||||||
|
|
||||||
# Profile Memory
|
# Profile Memory
|
||||||
|
|||||||
@@ -39,17 +39,34 @@ TOOL_DEFINITIONS = [
|
|||||||
"function": {
|
"function": {
|
||||||
"name": "transform_view",
|
"name": "transform_view",
|
||||||
"description": (
|
"description": (
|
||||||
"将一张图片转换为多个不同视角。"
|
"将一张图片转换为多个不同视角。需要用户先上传参考图。\n"
|
||||||
"使用 Zero123++ 模型从单张图片生成 6 个固定视角的图片。"
|
"可选模型：\n"
|
||||||
"适用于建筑、物体等需要从不同角度查看的场景。"
|
"- zero123plus（默认）：~15s/次，Zero123++ 直接输出 6 个固定视角"
|
||||||
"输入图片必须是正方形（或会被自动裁切为正方形），建议分辨率 >= 320x320。"
|
"（方位角 30/90/150/210/270/330°，仰角交替 30/-20°），适合快速预览，"
|
||||||
"输出 6 个视角：方位角 30°/90°/150°/210°/270°/330°，"
|
"对建筑大角度可能有错位。\n"
|
||||||
"仰角交替为 30°/-20°（正俯视/微仰视）。"
|
"- trellis：~105s/次，先 3D 重建再重绘，"
|
||||||
"此工具需要参考图作为输入——必须先有用户上传的图片才能使用。"
|
"支持任意方位角 + 原画风保留，适合卡通描边风格建筑。"
|
||||||
),
|
),
|
||||||
"parameters": {
|
"parameters": {
|
||||||
"type": "object",
|
"type": "object",
|
||||||
"properties": {},
|
"properties": {
|
||||||
|
"model_id": {
|
||||||
|
"type": "string",
|
||||||
|
"enum": ["zero123plus", "trellis"],
|
||||||
|
"default": "zero123plus",
|
||||||
|
"description": "视角变换模型；默认 zero123plus（快），trellis 画风还原更强但慢",
|
||||||
|
},
|
||||||
|
"azimuths": {
|
||||||
|
"type": "array",
|
||||||
|
"items": {"type": "integer"},
|
||||||
|
"description": "mesh 管道专用：自定义方位角数组（0-359），默认 [0,60,120,180,240,300]",
|
||||||
|
},
|
||||||
|
"preserve_style": {
|
||||||
|
"type": "boolean",
|
||||||
|
"default": True,
|
||||||
|
"description": "mesh 管道专用：是否对抽帧结果走 IP-Adapter+ControlNet 重绘还原原画风",
|
||||||
|
},
|
||||||
|
},
|
||||||
"required": [],
|
"required": [],
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
@@ -92,7 +109,13 @@ async def execute_tool(
|
|||||||
"success": False,
|
"success": False,
|
||||||
"error": "视角变换需要一张输入图片，请先上传参考图",
|
"error": "视角变换需要一张输入图片，请先上传参考图",
|
||||||
}
|
}
|
||||||
result = await transform_view(ref_image_urls[0])
|
result = await transform_view(
|
||||||
|
ref_image_urls[0],
|
||||||
|
model_id=arguments.get("model_id"),
|
||||||
|
azimuths=arguments.get("azimuths"),
|
||||||
|
elevations=arguments.get("elevations"),
|
||||||
|
preserve_style=arguments.get("preserve_style", True),
|
||||||
|
)
|
||||||
return result
|
return result
|
||||||
|
|
||||||
return {"success": False, "error": f"未知工具: {tool_name}"}
|
return {"success": False, "error": f"未知工具: {tool_name}"}
|
||||||
|
|||||||
@@ -225,9 +225,35 @@ IMAGE_MODELS: dict[str, dict[str, Any]] = {
|
|||||||
"output_format": "png",
|
"output_format": "png",
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
|
# Mesh 管道专用的内部模型（internal=True 不展示到前端下拉）：
|
||||||
|
# 输入两张图：image=原图做 IP-Adapter 风格参考；controlnet_input=normal/depth 结构参考。
|
||||||
|
# 用途：在 Stage 3 对 Trellis 抽出来的 normal 帧做二次重绘，还原原画风。
|
||||||
|
"ip-adapter-controlnet-depth": {
|
||||||
|
"id": "ip-adapter-controlnet-depth",
|
||||||
|
"name": "IP-Adapter + ControlNet Depth (内部)",
|
||||||
|
"provider": "replicate",
|
||||||
|
"model_id": "chigozienri/ip_adapter-sdxl-controlnet-depth:0436c8702ef52616be5c30948551b3af6a86c821cca9b01f11ac297624fff14c",
|
||||||
|
"description": "Mesh 管道 Stage 3 专用：IP-Adapter 保风格 + ControlNet 保几何",
|
||||||
|
"internal": True,
|
||||||
|
"supports_ref_image": True,
|
||||||
|
"ref_image_param": "image", # IP-Adapter 参考图字段
|
||||||
|
"default_params": {
|
||||||
|
"scale": 0.75, # IP-Adapter 权重（建议 0.7-0.8）
|
||||||
|
"controlnet_conditioning_scale": 0.8, # 结构约束（建议 0.7-0.9）
|
||||||
|
"prompt": "same building, same art style, consistent with reference",
|
||||||
|
"negative_prompt": "blurry, distorted, different style, realistic photo, photograph",
|
||||||
|
"num_outputs": 1,
|
||||||
|
"num_inference_steps": 30,
|
||||||
|
},
|
||||||
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def get_style_restore_model_id() -> str:
|
||||||
|
"""Mesh 管道 Stage 3 使用的内部模型短 ID。"""
|
||||||
|
return "ip-adapter-controlnet-depth"
|
||||||
|
|
||||||
|
|
||||||
# ─── 视角变换模型注册表 ─────────────────────────────────
|
# ─── 视角变换模型注册表 ─────────────────────────────────
|
||||||
#
|
#
|
||||||
# 视角变换模型不用于生图，而是将已有图片转换为不同视角。
|
# 视角变换模型不用于生图，而是将已有图片转换为不同视角。
|
||||||
@@ -240,6 +266,7 @@ VIEW_TRANSFORM_MODELS: dict[str, dict[str, Any]] = {
|
|||||||
"provider": "replicate",
|
"provider": "replicate",
|
||||||
"model_id": "jd7h/zero123plusplus:c69c6559a29011b576f1ff0371b3bc1add2856480c60520c7e9ce0b40a6e9052",
|
"model_id": "jd7h/zero123plusplus:c69c6559a29011b576f1ff0371b3bc1add2856480c60520c7e9ce0b40a6e9052",
|
||||||
"description": "单图生成 6 个固定视角，适合建筑/物体的多角度预览",
|
"description": "单图生成 6 个固定视角，适合建筑/物体的多角度预览",
|
||||||
|
"pipeline": "grid",
|
||||||
"output_views": [
|
"output_views": [
|
||||||
{"azimuth": 30, "elevation": 30},
|
{"azimuth": 30, "elevation": 30},
|
||||||
{"azimuth": 90, "elevation": -20},
|
{"azimuth": 90, "elevation": -20},
|
||||||
@@ -248,7 +275,46 @@ VIEW_TRANSFORM_MODELS: dict[str, dict[str, Any]] = {
|
|||||||
{"azimuth": 270, "elevation": 30},
|
{"azimuth": 270, "elevation": 30},
|
||||||
{"azimuth": 330, "elevation": -20},
|
{"azimuth": 330, "elevation": -20},
|
||||||
],
|
],
|
||||||
"grid_layout": {"cols": 3, "rows": 2},
|
"grid_layout": {"cols": 2, "rows": 3},
|
||||||
|
"enabled": True,
|
||||||
|
},
|
||||||
|
"trellis": {
|
||||||
|
"id": "trellis",
|
||||||
|
"name": "Trellis (Mesh Pipeline)",
|
||||||
|
"provider": "replicate",
|
||||||
|
"model_id": "firtoz/trellis:e8f6c45206993f297372f5436b90350817bd9b4a0d52d2a76df50c1c8afa2b3c",
|
||||||
|
"description": "3D 重建 + 任意视角 + 风格还原，建筑友好（~30s 重建 + 72s/张重绘）",
|
||||||
|
"pipeline": "mesh",
|
||||||
|
"default_params": {
|
||||||
|
"texture_size": 1024,
|
||||||
|
"mesh_simplify": 0.95,
|
||||||
|
"generate_color": True,
|
||||||
|
"generate_normal": True,
|
||||||
|
"generate_model": True,
|
||||||
|
"save_gaussian_ply": False,
|
||||||
|
"ss_sampling_steps": 12,
|
||||||
|
"slat_sampling_steps": 12,
|
||||||
|
"ss_guidance_strength": 7.5,
|
||||||
|
"slat_guidance_strength": 3.0,
|
||||||
|
},
|
||||||
|
"default_azimuths": [0, 60, 120, 180, 240, 300],
|
||||||
|
"default_elevations": [0, 0, 0, 0, 0, 0],
|
||||||
|
"enabled": True,
|
||||||
|
},
|
||||||
|
"hunyuan3d": {
|
||||||
|
"id": "hunyuan3d",
|
||||||
|
"name": "Hunyuan3D-2 (高质量)",
|
||||||
|
"provider": "replicate",
|
||||||
|
"model_id": "tencent/hunyuan3d-2:b1b9449a1277e10402781c5d41eb30c0a0683504fb23fab591ca9dfc2aabe1cb",
|
||||||
|
"description": "几何质量最佳（~127s），需自定义渲染器（二期启用）",
|
||||||
|
"pipeline": "mesh",
|
||||||
|
"default_params": {
|
||||||
|
"steps": 50,
|
||||||
|
"guidance_scale": 5.5,
|
||||||
|
"octree_resolution": 256,
|
||||||
|
"remove_background": True,
|
||||||
|
},
|
||||||
|
"enabled": False,
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -261,14 +327,16 @@ def get_view_transform_model_config(model_id: str | None = None) -> dict[str, An
|
|||||||
|
|
||||||
|
|
||||||
def get_view_transform_models_list() -> list[dict]:
|
def get_view_transform_models_list() -> list[dict]:
|
||||||
"""返回前端下拉列表所需的视角变换模型摘要信息。"""
|
"""返回前端下拉列表所需的视角变换模型摘要信息（只包含 enabled=True 的）。"""
|
||||||
return [
|
return [
|
||||||
{
|
{
|
||||||
"id": cfg["id"],
|
"id": cfg["id"],
|
||||||
"name": cfg["name"],
|
"name": cfg["name"],
|
||||||
"description": cfg["description"],
|
"description": cfg["description"],
|
||||||
|
"pipeline": cfg.get("pipeline", "grid"),
|
||||||
}
|
}
|
||||||
for cfg in VIEW_TRANSFORM_MODELS.values()
|
for cfg in VIEW_TRANSFORM_MODELS.values()
|
||||||
|
if cfg.get("enabled", True)
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
@@ -297,7 +365,7 @@ def get_ref_image_model_id() -> str | None:
|
|||||||
|
|
||||||
|
|
||||||
def get_image_models_list() -> list[dict]:
|
def get_image_models_list() -> list[dict]:
|
||||||
"""返回前端下拉列表所需的模型摘要信息。"""
|
"""返回前端下拉列表所需的模型摘要信息（过滤掉 internal=True 的内部模型）。"""
|
||||||
return [
|
return [
|
||||||
{
|
{
|
||||||
"id": cfg["id"],
|
"id": cfg["id"],
|
||||||
@@ -306,6 +374,7 @@ def get_image_models_list() -> list[dict]:
|
|||||||
"supports_ref_image": cfg.get("supports_ref_image", False),
|
"supports_ref_image": cfg.get("supports_ref_image", False),
|
||||||
}
|
}
|
||||||
for cfg in IMAGE_MODELS.values()
|
for cfg in IMAGE_MODELS.values()
|
||||||
|
if not cfg.get("internal", False)
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
189
art-agent/backend/app/services/mesh_generator.py
Normal file
189
art-agent/backend/app/services/mesh_generator.py
Normal file
@@ -0,0 +1,189 @@
|
|||||||
|
"""3D Mesh 生成服务 — 阶段 1：单图 → textured .glb + 360° 预渲染视频。
|
||||||
|
|
||||||
|
当前支持：
|
||||||
|
- Trellis (firtoz/trellis)：~30s，$0.041/次，自带 color_video + normal_video + .glb
|
||||||
|
- Hunyuan3D-2 (tencent/hunyuan3d-2)：~127s，$0.12/次，仅 .glb 无预渲染视频（二期启用）
|
||||||
|
"""
|
||||||
|
|
||||||
|
import logging
|
||||||
|
import os
|
||||||
|
import uuid
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
import httpx
|
||||||
|
|
||||||
|
from app.config import get_view_transform_model_config
|
||||||
|
from app.services.image_gen import _make_replicate_client, GENERATED_DIR, to_data_uri
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
_replicate_client = _make_replicate_client()
|
||||||
|
|
||||||
|
SUPPORTED_EXTS = {
|
||||||
|
"model_file": ".glb",
|
||||||
|
"color_video": ".mp4",
|
||||||
|
"normal_video": ".mp4",
|
||||||
|
"combined_video": ".mp4",
|
||||||
|
"gaussian_ply": ".ply",
|
||||||
|
"mesh": ".glb",
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
async def _download_asset(url: str, ext: str, prefix: str) -> Path:
|
||||||
|
"""下载远程资源到 generated/ 目录，返回本地路径。"""
|
||||||
|
filename = f"{prefix}_{uuid.uuid4().hex[:12]}{ext}"
|
||||||
|
filepath = GENERATED_DIR / filename
|
||||||
|
proxy = os.environ.get("HTTPS_PROXY") or os.environ.get("HTTP_PROXY")
|
||||||
|
async with httpx.AsyncClient(proxy=proxy, timeout=httpx.Timeout(300.0)) as client:
|
||||||
|
resp = await client.get(url, follow_redirects=True)
|
||||||
|
resp.raise_for_status()
|
||||||
|
filepath.write_bytes(resp.content)
|
||||||
|
return filepath
|
||||||
|
|
||||||
|
|
||||||
|
def _to_url(value: Any) -> str | None:
|
||||||
|
"""把 Replicate FileOutput / str / None 统一转为 URL 字符串。"""
|
||||||
|
if value is None:
|
||||||
|
return None
|
||||||
|
s = str(value)
|
||||||
|
if s.startswith("http://") or s.startswith("https://"):
|
||||||
|
return s
|
||||||
|
return None
|
||||||
|
|
||||||
|
|
||||||
|
async def generate_with_trellis(
|
||||||
|
image_path: str,
|
||||||
|
params: dict[str, Any] | None = None,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
"""调用 Trellis 做单图 3D 重建，下载所有输出资产到本地。
|
||||||
|
|
||||||
|
Args:
|
||||||
|
image_path: 输入图（本地路径 / data URI / URL）
|
||||||
|
params: 覆盖 default_params 的可选参数字典
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
{
|
||||||
|
"success": bool,
|
||||||
|
"glb_path": "/generated/trellis_xxx.glb" | None,
|
||||||
|
"color_video_path": "/generated/trellis_xxx_color.mp4" | None,
|
||||||
|
"normal_video_path": "/generated/trellis_xxx_normal.mp4" | None,
|
||||||
|
"combined_video_path": ...,
|
||||||
|
"raw_output_keys": [...], # 调试用
|
||||||
|
"error": str | None,
|
||||||
|
}
|
||||||
|
"""
|
||||||
|
config = get_view_transform_model_config("trellis")
|
||||||
|
replicate_model_id = config["model_id"]
|
||||||
|
default_params = dict(config.get("default_params", {}))
|
||||||
|
if params:
|
||||||
|
default_params.update(params)
|
||||||
|
|
||||||
|
GENERATED_DIR.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
|
try:
|
||||||
|
image_uri = to_data_uri(image_path)
|
||||||
|
# firtoz/trellis:e8f6c452... 这个部署版的 schema：
|
||||||
|
# - 输入必须用 `images` 数组（传 `image` 单数会 422）
|
||||||
|
# - 输出字段 `color_video` 和 `normal_video` 实测恒为 null
|
||||||
|
# - 实际可用的视频只有 `combined_video`（color+normal 左右并排）
|
||||||
|
# 因此 Phase 2 抽帧时从 combined_video 切左半得 color、切右半得 normal。
|
||||||
|
input_params: dict[str, Any] = {
|
||||||
|
"images": [image_uri],
|
||||||
|
"randomize_seed": False,
|
||||||
|
"seed": 0,
|
||||||
|
**default_params,
|
||||||
|
}
|
||||||
|
|
||||||
|
logger.info(
|
||||||
|
"调用 Trellis 进行 3D 重建：model=%s, params=%s",
|
||||||
|
replicate_model_id,
|
||||||
|
{k: v for k, v in input_params.items() if k != "images"},
|
||||||
|
)
|
||||||
|
output = await _replicate_client.async_run(
|
||||||
|
replicate_model_id, input=input_params, wait=False
|
||||||
|
)
|
||||||
|
|
||||||
|
if not isinstance(output, dict):
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"error": f"Trellis 返回非字典输出：{type(output).__name__} / {str(output)[:200]}",
|
||||||
|
"raw_output_keys": [],
|
||||||
|
}
|
||||||
|
|
||||||
|
raw_keys = list(output.keys())
|
||||||
|
logger.info("Trellis 返回字段：%s", raw_keys)
|
||||||
|
|
||||||
|
# 按已知字段挨个下载
|
||||||
|
result: dict[str, Any] = {
|
||||||
|
"success": True,
|
||||||
|
"raw_output_keys": raw_keys,
|
||||||
|
"error": None,
|
||||||
|
}
|
||||||
|
download_map = [
|
||||||
|
("model_file", "glb_path", ".glb", "trellis"),
|
||||||
|
("color_video", "color_video_path", ".mp4", "trellis_color"),
|
||||||
|
("normal_video", "normal_video_path", ".mp4", "trellis_normal"),
|
||||||
|
("combined_video", "combined_video_path", ".mp4", "trellis_combined"),
|
||||||
|
]
|
||||||
|
|
||||||
|
for src_key, dst_key, ext, prefix in download_map:
|
||||||
|
if src_key not in output:
|
||||||
|
result[dst_key] = None
|
||||||
|
continue
|
||||||
|
url = _to_url(output[src_key])
|
||||||
|
if not url:
|
||||||
|
logger.warning("Trellis 字段 %s 不是有效 URL：%s", src_key, output[src_key])
|
||||||
|
result[dst_key] = None
|
||||||
|
continue
|
||||||
|
try:
|
||||||
|
local_path = await _download_asset(url, ext, prefix)
|
||||||
|
result[dst_key] = f"/generated/{local_path.name}"
|
||||||
|
logger.info("已下载 %s → %s", src_key, local_path.name)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error("下载 %s 失败：%s", src_key, e)
|
||||||
|
result[dst_key] = None
|
||||||
|
|
||||||
|
# 阶段 2 抽帧的优先级：color_video > combined_video（切左半）
|
||||||
|
# 只要其中一个可用即算成功
|
||||||
|
has_color_source = bool(result.get("color_video_path")) or bool(
|
||||||
|
result.get("combined_video_path")
|
||||||
|
)
|
||||||
|
if not has_color_source:
|
||||||
|
result["success"] = False
|
||||||
|
result["error"] = (
|
||||||
|
"Trellis 未返回 color_video 或 combined_video，无法进入阶段 2 抽帧；"
|
||||||
|
f"实际返回字段：{raw_keys}"
|
||||||
|
)
|
||||||
|
|
||||||
|
return result
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
detail = str(e) or f"{type(e).__name__}: {repr(e)}"
|
||||||
|
logger.error("Trellis 调用失败：%s", detail, exc_info=True)
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"error": detail,
|
||||||
|
"raw_output_keys": [],
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
async def generate_mesh(
|
||||||
|
image_path: str,
|
||||||
|
model_id: str = "trellis",
|
||||||
|
params: dict[str, Any] | None = None,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
"""统一入口：按 model_id 分发到具体实现。"""
|
||||||
|
if model_id == "trellis":
|
||||||
|
return await generate_with_trellis(image_path, params)
|
||||||
|
if model_id == "hunyuan3d":
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"error": "Hunyuan3D-2 (一期未启用，待二期接入自定义渲染)",
|
||||||
|
"raw_output_keys": [],
|
||||||
|
}
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"error": f"未知 mesh 模型：{model_id}",
|
||||||
|
"raw_output_keys": [],
|
||||||
|
}
|
||||||
180
art-agent/backend/app/services/style_restorer.py
Normal file
180
art-agent/backend/app/services/style_restorer.py
Normal file
@@ -0,0 +1,180 @@
|
|||||||
|
"""阶段 3：对 Trellis 抽帧结果做 IP-Adapter + ControlNet 重绘，还原原画风。
|
||||||
|
|
||||||
|
输入：
|
||||||
|
- original_image：用户上传的原图（提供风格 / IP-Adapter 参考）
|
||||||
|
- structure_image：Stage 2 抽出的 normal 帧（提供几何 / ControlNet 结构约束）
|
||||||
|
|
||||||
|
输出：
|
||||||
|
- 单张保留原画风且视角正确的 PNG，落盘到 GENERATED_DIR/ 下
|
||||||
|
|
||||||
|
模型：chigozienri/ip_adapter-sdxl-controlnet-depth（配置见 config.IMAGE_MODELS）
|
||||||
|
- $0.07/张，~72s，硬件 L40S
|
||||||
|
- `image` 字段 = IP-Adapter 参考图（风格源）
|
||||||
|
- `controlnet_input` 字段 = 结构参考图（当前一期传 normal 帧作为 depth 近似）
|
||||||
|
|
||||||
|
调参建议（可在 IMAGE_MODELS 默认值基础上覆盖）：
|
||||||
|
- scale (IP-Adapter 权重): 0.7-0.8，越高越贴近原图风格
|
||||||
|
- controlnet_conditioning_scale (结构权重): 0.7-0.9，越高越保几何
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import asyncio
|
||||||
|
import logging
|
||||||
|
import os
|
||||||
|
import uuid
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
import httpx
|
||||||
|
|
||||||
|
from app.config import get_image_model_config, get_style_restore_model_id
|
||||||
|
from app.services.image_gen import GENERATED_DIR, _make_replicate_client, to_data_uri
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
_replicate_client = _make_replicate_client()
|
||||||
|
|
||||||
|
|
||||||
|
async def _download_image(url: str, prefix: str) -> Path:
|
||||||
|
"""把 Replicate 返回的图片下载到 generated/。"""
|
||||||
|
filename = f"{prefix}_{uuid.uuid4().hex[:12]}.png"
|
||||||
|
filepath = GENERATED_DIR / filename
|
||||||
|
proxy = os.environ.get("HTTPS_PROXY") or os.environ.get("HTTP_PROXY")
|
||||||
|
async with httpx.AsyncClient(proxy=proxy, timeout=httpx.Timeout(180.0)) as client:
|
||||||
|
resp = await client.get(url, follow_redirects=True)
|
||||||
|
resp.raise_for_status()
|
||||||
|
filepath.write_bytes(resp.content)
|
||||||
|
return filepath
|
||||||
|
|
||||||
|
|
||||||
|
def _first_url(output: Any) -> str | None:
|
||||||
|
"""Replicate 输出有时是 list[FileOutput]、有时是单个；统一取第一张。"""
|
||||||
|
if output is None:
|
||||||
|
return None
|
||||||
|
if isinstance(output, list):
|
||||||
|
if not output:
|
||||||
|
return None
|
||||||
|
return str(output[0])
|
||||||
|
return str(output)
|
||||||
|
|
||||||
|
|
||||||
|
async def restore(
|
||||||
|
original_image: str,
|
||||||
|
structure_image: str,
|
||||||
|
azimuth: int = 0,
|
||||||
|
elevation: int = 0,
|
||||||
|
params: dict[str, Any] | None = None,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
"""对单张 normal 帧做 IP-Adapter + ControlNet 重绘。
|
||||||
|
|
||||||
|
Args:
|
||||||
|
original_image: 用户原图，本地路径 / data URI / URL 均可
|
||||||
|
structure_image: Stage 2 抽出的 normal 帧，同上
|
||||||
|
azimuth / elevation: 仅用于日志与返回元数据，不参与模型调用
|
||||||
|
params: 覆盖默认参数的字典（scale / controlnet_conditioning_scale / prompt 等）
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
{
|
||||||
|
"success": bool,
|
||||||
|
"url": "/generated/restyled_xxx.png" | None,
|
||||||
|
"azimuth": int,
|
||||||
|
"elevation": int,
|
||||||
|
"error": str | None,
|
||||||
|
}
|
||||||
|
"""
|
||||||
|
config = get_image_model_config(get_style_restore_model_id())
|
||||||
|
replicate_model_id = config["model_id"]
|
||||||
|
merged_params = dict(config.get("default_params", {}))
|
||||||
|
if params:
|
||||||
|
merged_params.update(params)
|
||||||
|
|
||||||
|
GENERATED_DIR.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
|
try:
|
||||||
|
image_uri = to_data_uri(original_image)
|
||||||
|
structure_uri = to_data_uri(structure_image)
|
||||||
|
|
||||||
|
input_params: dict[str, Any] = {
|
||||||
|
"image": image_uri, # IP-Adapter 参考图 = 用户原图
|
||||||
|
"controlnet_input": structure_uri, # 结构参考 = normal 帧
|
||||||
|
**merged_params,
|
||||||
|
}
|
||||||
|
|
||||||
|
logger.info(
|
||||||
|
"Stage 3 重绘 az=%d el=%d: scale=%s, cn_scale=%s",
|
||||||
|
azimuth, elevation,
|
||||||
|
merged_params.get("scale"),
|
||||||
|
merged_params.get("controlnet_conditioning_scale"),
|
||||||
|
)
|
||||||
|
|
||||||
|
output = await _replicate_client.async_run(
|
||||||
|
replicate_model_id, input=input_params, wait=False
|
||||||
|
)
|
||||||
|
|
||||||
|
url = _first_url(output)
|
||||||
|
if not url or not (url.startswith("http://") or url.startswith("https://")):
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"url": None,
|
||||||
|
"azimuth": azimuth,
|
||||||
|
"elevation": elevation,
|
||||||
|
"error": f"模型未返回有效图片 URL: {str(output)[:200]}",
|
||||||
|
}
|
||||||
|
|
||||||
|
local = await _download_image(url, prefix=f"restyled_az{azimuth}_el{elevation}")
|
||||||
|
return {
|
||||||
|
"success": True,
|
||||||
|
"url": f"/generated/{local.name}",
|
||||||
|
"azimuth": azimuth,
|
||||||
|
"elevation": elevation,
|
||||||
|
"error": None,
|
||||||
|
}
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
detail = str(e) or f"{type(e).__name__}: {repr(e)}"
|
||||||
|
logger.error(
|
||||||
|
"Stage 3 重绘失败 az=%d el=%d: %s", azimuth, elevation, detail, exc_info=True
|
||||||
|
)
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"url": None,
|
||||||
|
"azimuth": azimuth,
|
||||||
|
"elevation": elevation,
|
||||||
|
"error": detail,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
async def restore_batch(
|
||||||
|
original_image: str,
|
||||||
|
frames: list[dict[str, Any]],
|
||||||
|
params: dict[str, Any] | None = None,
|
||||||
|
concurrency: int = 3,
|
||||||
|
) -> list[dict[str, Any]]:
|
||||||
|
"""对一批 frames 做 Stage 3 重绘，带并发控制。
|
||||||
|
|
||||||
|
Args:
|
||||||
|
original_image: 用户原图（所有帧共用同一张风格参考）
|
||||||
|
frames: [{"az", "el", "normal_png", ...}, ...]，normal_png 作为结构参考
|
||||||
|
params: 透传给 restore() 的覆盖参数
|
||||||
|
concurrency: 最大并发数；Replicate 并发打太猛容易撞 rate limit，3 比较稳
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
列表，顺序与 frames 对齐，元素与 restore() 的返回一致。
|
||||||
|
"""
|
||||||
|
if not frames:
|
||||||
|
return []
|
||||||
|
|
||||||
|
sem = asyncio.Semaphore(max(1, concurrency))
|
||||||
|
|
||||||
|
async def _one(f: dict[str, Any]) -> dict[str, Any]:
|
||||||
|
async with sem:
|
||||||
|
return await restore(
|
||||||
|
original_image=original_image,
|
||||||
|
structure_image=f["normal_png"],
|
||||||
|
azimuth=int(f.get("az", 0)),
|
||||||
|
elevation=int(f.get("el", 0)),
|
||||||
|
params=params,
|
||||||
|
)
|
||||||
|
|
||||||
|
return await asyncio.gather(*[_one(f) for f in frames])
|
||||||
191
art-agent/backend/app/services/video_frame_extractor.py
Normal file
191
art-agent/backend/app/services/video_frame_extractor.py
Normal file
@@ -0,0 +1,191 @@
|
|||||||
|
"""阶段 2：从 Trellis combined_video 抽帧 + 切左右半得到 color / normal 帧。
|
||||||
|
|
||||||
|
Trellis (firtoz/trellis) 部署版 `e8f6c452...` 实测只返回 `combined_video`
|
||||||
|
（color 和 normal 左右并排 mp4，约 5 秒 360° 水平环绕），不再单独返回
|
||||||
|
`color_video` / `normal_video`（详见 PF-20260420-1600）。
|
||||||
|
|
||||||
|
本模块职责：
|
||||||
|
1. 对给定 combined_video 做一次全帧抽取（imageio-ffmpeg 自带二进制，无需系统 ffmpeg）
|
||||||
|
2. 按 azimuth / total_rotation_deg 映射到帧索引并挑出对应帧
|
||||||
|
3. 用 PIL 切左半 → color png、右半 → normal png，落盘到 GENERATED_DIR
|
||||||
|
4. 返回 [{az, el, frame_idx, color_png, normal_png}, ...]
|
||||||
|
|
||||||
|
一期仅支持 elevation=0（Trellis 的 combined_video 就是平视一圈，本身没有仰俯）。
|
||||||
|
需要自由 elevation 时走 Phase 5 的 mesh_renderer 路径（pyrender / Blender headless）。
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import asyncio
|
||||||
|
import logging
|
||||||
|
import subprocess
|
||||||
|
import uuid
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
import imageio_ffmpeg # 提供静态 ffmpeg 二进制，避免依赖系统 ffmpeg
|
||||||
|
from PIL import Image
|
||||||
|
|
||||||
|
from app.services.image_gen import GENERATED_DIR
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
FFMPEG_EXE = imageio_ffmpeg.get_ffmpeg_exe()
|
||||||
|
|
||||||
|
|
||||||
|
def _resolve_local_path(path_or_url: str) -> Path:
|
||||||
|
"""把 mesh_generator 返回的 '/generated/xxx.mp4' 解析为真实磁盘路径。
|
||||||
|
|
||||||
|
兼容三种输入：
|
||||||
|
- '/generated/xxx.mp4' → GENERATED_DIR / xxx.mp4
|
||||||
|
- 'D:/abs/path/xxx.mp4' → Path 原样
|
||||||
|
- 'xxx.mp4' → Path 原样（调用方自行保证）
|
||||||
|
"""
|
||||||
|
if not path_or_url:
|
||||||
|
raise ValueError("combined_video_path 为空")
|
||||||
|
if path_or_url.startswith("/generated/"):
|
||||||
|
return GENERATED_DIR / Path(path_or_url).name
|
||||||
|
return Path(path_or_url)
|
||||||
|
|
||||||
|
|
||||||
|
def _extract_all_frames(video_path: Path, temp_dir: Path) -> list[Path]:
|
||||||
|
"""把 video 的所有帧抽到 temp_dir，返回按文件名排序的帧列表。
|
||||||
|
|
||||||
|
对 Trellis ~5s 的 combined_video（~100-150 帧）这种量级是 OK 的，
|
||||||
|
比起"用 -ss 逐帧抽取"更省心、角度映射也更稳。
|
||||||
|
"""
|
||||||
|
temp_dir.mkdir(parents=True, exist_ok=True)
|
||||||
|
out_pattern = str(temp_dir / "f%05d.png")
|
||||||
|
cmd = [
|
||||||
|
FFMPEG_EXE,
|
||||||
|
"-y",
|
||||||
|
"-hide_banner",
|
||||||
|
"-loglevel", "error",
|
||||||
|
"-i", str(video_path),
|
||||||
|
"-vsync", "0",
|
||||||
|
out_pattern,
|
||||||
|
]
|
||||||
|
logger.info("ffmpeg extract-all: %s", " ".join(cmd))
|
||||||
|
proc = subprocess.run(cmd, capture_output=True, text=True)
|
||||||
|
if proc.returncode != 0:
|
||||||
|
raise RuntimeError(
|
||||||
|
f"ffmpeg 抽帧失败 (code {proc.returncode}): stderr={proc.stderr[-500:]}"
|
||||||
|
)
|
||||||
|
frames = sorted(temp_dir.glob("f*.png"))
|
||||||
|
if not frames:
|
||||||
|
raise RuntimeError(
|
||||||
|
f"ffmpeg 执行成功但没产出帧：{video_path}；stderr={proc.stderr[-500:]}"
|
||||||
|
)
|
||||||
|
return frames
|
||||||
|
|
||||||
|
|
||||||
|
def _split_combined_frame(
|
||||||
|
frame_path: Path,
|
||||||
|
out_prefix: str,
|
||||||
|
az: int,
|
||||||
|
el: int,
|
||||||
|
) -> tuple[Path, Path]:
|
||||||
|
"""把 combined 帧按中线切成 color（左）+ normal（右）两张图。"""
|
||||||
|
img = Image.open(frame_path)
|
||||||
|
w, h = img.size
|
||||||
|
mid = w // 2
|
||||||
|
color = img.crop((0, 0, mid, h))
|
||||||
|
normal = img.crop((mid, 0, w, h))
|
||||||
|
|
||||||
|
color_name = f"view_{out_prefix}_az{az}_el{el}_color.png"
|
||||||
|
normal_name = f"view_{out_prefix}_az{az}_el{el}_normal.png"
|
||||||
|
color_path = GENERATED_DIR / color_name
|
||||||
|
normal_path = GENERATED_DIR / normal_name
|
||||||
|
color.save(color_path, "PNG")
|
||||||
|
normal.save(normal_path, "PNG")
|
||||||
|
return color_path, normal_path
|
||||||
|
|
||||||
|
|
||||||
|
def _cleanup_dir(dir_path: Path) -> None:
|
||||||
|
"""静默删除临时目录及其所有文件，失败不抛。"""
|
||||||
|
if not dir_path.exists():
|
||||||
|
return
|
||||||
|
for f in dir_path.glob("*"):
|
||||||
|
try:
|
||||||
|
f.unlink()
|
||||||
|
except OSError:
|
||||||
|
pass
|
||||||
|
try:
|
||||||
|
dir_path.rmdir()
|
||||||
|
except OSError:
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
def _do_extract(
|
||||||
|
video: Path,
|
||||||
|
azimuths: list[int],
|
||||||
|
elevations: list[int],
|
||||||
|
total_rotation_deg: int,
|
||||||
|
) -> list[dict[str, Any]]:
|
||||||
|
"""同步版抽帧逻辑，供 async 版本用 run_in_executor 包起来跑。"""
|
||||||
|
batch_id = uuid.uuid4().hex[:8]
|
||||||
|
temp_dir = GENERATED_DIR / f"_frames_{batch_id}"
|
||||||
|
|
||||||
|
try:
|
||||||
|
frames = _extract_all_frames(video, temp_dir)
|
||||||
|
total = len(frames)
|
||||||
|
logger.info("combined_video %s 抽出 %d 帧，总时长~%.2fs (按 24fps 估)",
|
||||||
|
video.name, total, total / 24.0)
|
||||||
|
|
||||||
|
results: list[dict[str, Any]] = []
|
||||||
|
for az, el in zip(azimuths, elevations):
|
||||||
|
# az 归一化到 [0, total_rotation_deg)，再映射到 [0, total) 整数索引
|
||||||
|
az_mod = az % total_rotation_deg if total_rotation_deg > 0 else 0
|
||||||
|
frame_idx = int(round(az_mod / total_rotation_deg * total)) % total if total > 0 else 0
|
||||||
|
src_frame = frames[frame_idx]
|
||||||
|
color_path, normal_path = _split_combined_frame(src_frame, batch_id, az, el)
|
||||||
|
results.append({
|
||||||
|
"az": az,
|
||||||
|
"el": el,
|
||||||
|
"frame_idx": frame_idx,
|
||||||
|
"color_png": f"/generated/{color_path.name}",
|
||||||
|
"normal_png": f"/generated/{normal_path.name}",
|
||||||
|
})
|
||||||
|
return results
|
||||||
|
finally:
|
||||||
|
_cleanup_dir(temp_dir)
|
||||||
|
|
||||||
|
|
||||||
|
async def extract_by_azimuth(
|
||||||
|
combined_video_path: str,
|
||||||
|
azimuths: list[int],
|
||||||
|
elevations: list[int] | None = None,
|
||||||
|
total_rotation_deg: int = 360,
|
||||||
|
) -> list[dict[str, Any]]:
|
||||||
|
"""按 azimuth 列表从 combined_video 抽帧 + 切左右半。
|
||||||
|
|
||||||
|
Args:
|
||||||
|
combined_video_path: '/generated/trellis_combined_xxx.mp4' 或本地磁盘路径
|
||||||
|
azimuths: 方位角数组，单位度（0-360，允许大于 360 会自动取模）
|
||||||
|
elevations: 仰角数组；长度须等于 azimuths；一期所有值被忽略，保留字段以便后续扩展
|
||||||
|
total_rotation_deg: combined_video 覆盖的水平旋转范围；Trellis 默认 360
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
[{"az": 60, "el": 0, "frame_idx": 20,
|
||||||
|
"color_png": "/generated/view_xxx_az60_el0_color.png",
|
||||||
|
"normal_png": "/generated/view_xxx_az60_el0_normal.png"}, ...]
|
||||||
|
"""
|
||||||
|
video = _resolve_local_path(combined_video_path)
|
||||||
|
if not video.exists():
|
||||||
|
raise FileNotFoundError(f"combined_video 文件不存在：{video}")
|
||||||
|
if not azimuths:
|
||||||
|
return []
|
||||||
|
if elevations is None:
|
||||||
|
elevations = [0] * len(azimuths)
|
||||||
|
if len(elevations) != len(azimuths):
|
||||||
|
raise ValueError(
|
||||||
|
f"azimuths / elevations 长度不一致：{len(azimuths)} vs {len(elevations)}"
|
||||||
|
)
|
||||||
|
|
||||||
|
# ffmpeg + PIL 是 CPU/IO 阻塞的，丢到线程池里跑避免堵死事件循环
|
||||||
|
loop = asyncio.get_running_loop()
|
||||||
|
return await loop.run_in_executor(
|
||||||
|
None,
|
||||||
|
_do_extract,
|
||||||
|
video, azimuths, elevations, total_rotation_deg,
|
||||||
|
)
|
||||||
@@ -1,4 +1,8 @@
|
|||||||
"""视角变换服务 — 调用 Zero123++ 等模型，将单张图片转为多视角图片。"""
|
"""视角变换服务 — 调度单图→多视角生成，支持两种管道：
|
||||||
|
|
||||||
|
- grid 管道：Zero123++ 直接输出 6 宫格拼接图，切分后得到固定 6 视角。
|
||||||
|
- mesh 管道：Trellis/Hunyuan3D → .glb + 预渲染视频 → 抽帧 → 可选风格还原。
|
||||||
|
"""
|
||||||
|
|
||||||
import base64
|
import base64
|
||||||
import logging
|
import logging
|
||||||
@@ -13,6 +17,9 @@ from PIL import Image
|
|||||||
|
|
||||||
from app.config import get_view_transform_model_config
|
from app.config import get_view_transform_model_config
|
||||||
from app.services.image_gen import _make_replicate_client, GENERATED_DIR, to_data_uri
|
from app.services.image_gen import _make_replicate_client, GENERATED_DIR, to_data_uri
|
||||||
|
from app.services import mesh_generator, style_restorer, video_frame_extractor
|
||||||
|
|
||||||
|
DEFAULT_MESH_AZIMUTHS = [0, 60, 120, 180, 240, 300]
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -29,9 +36,30 @@ def _split_grid_image(
|
|||||||
|
|
||||||
返回格式：[{"url": "/generated/xxx.png", "azimuth": 30, "elevation": 30}, ...]
|
返回格式：[{"url": "/generated/xxx.png", "azimuth": 30, "elevation": 30}, ...]
|
||||||
Grid 布局从左到右、从上到下依次对应 view_labels 中的视角。
|
Grid 布局从左到右、从上到下依次对应 view_labels 中的视角。
|
||||||
|
|
||||||
|
由于不同 Replicate 部署版本输出的拼接图布局可能不同（有的是 3列×2行 的
|
||||||
|
宽图，有的是 2列×3行 的高图），这里会根据实际图像长宽比自动纠正 cols/rows——
|
||||||
|
假定每个单视角为正方形，按 aspect ratio 推断真实布局，防止切图错位。
|
||||||
"""
|
"""
|
||||||
img = Image.open(image_path)
|
img = Image.open(image_path)
|
||||||
w, h = img.size
|
w, h = img.size
|
||||||
|
|
||||||
|
expected_cells = cols * rows
|
||||||
|
if expected_cells > 0 and len(view_labels) == expected_cells:
|
||||||
|
# 假定每个视角为正方形：真实 aspect ratio = cols / rows
|
||||||
|
configured_ratio = cols / rows
|
||||||
|
actual_ratio = w / h if h else configured_ratio
|
||||||
|
# 如果实际 ratio 与配置差异较大（超过 20%），判定为布局反了
|
||||||
|
if actual_ratio > 0 and (
|
||||||
|
max(configured_ratio, actual_ratio) / min(configured_ratio, actual_ratio) > 1.2
|
||||||
|
):
|
||||||
|
logger.warning(
|
||||||
|
"Grid 布局与实际图像不匹配：配置 cols=%d rows=%d（ratio=%.2f），"
|
||||||
|
"实际图像 %dx%d（ratio=%.2f），自动交换 cols/rows。",
|
||||||
|
cols, rows, configured_ratio, w, h, actual_ratio,
|
||||||
|
)
|
||||||
|
cols, rows = rows, cols
|
||||||
|
|
||||||
cell_w = w // cols
|
cell_w = w // cols
|
||||||
cell_h = h // rows
|
cell_h = h // rows
|
||||||
|
|
||||||
@@ -73,30 +101,60 @@ async def _download_to_local(url: str) -> Path:
|
|||||||
async def transform_view(
|
async def transform_view(
|
||||||
image_path: str,
|
image_path: str,
|
||||||
model_id: str | None = None,
|
model_id: str | None = None,
|
||||||
|
azimuths: list[int] | None = None,
|
||||||
|
elevations: list[int] | None = None,
|
||||||
|
preserve_style: bool = True,
|
||||||
) -> dict[str, Any]:
|
) -> dict[str, Any]:
|
||||||
"""调用视角变换模型，返回多视角图片列表。
|
"""调用视角变换模型，返回多视角图片列表。
|
||||||
|
|
||||||
Args:
|
Args:
|
||||||
image_path: 输入图片路径（本地路径、data URI 或 URL）
|
image_path: 输入图片路径（本地路径、data URI 或 URL）
|
||||||
model_id: 视角变换模型 ID，默认 zero123plus
|
model_id: 视角变换模型 ID（zero123plus / trellis / hunyuan3d）
|
||||||
|
azimuths: mesh 管道专用，方位角数组
|
||||||
|
elevations: mesh 管道专用，仰角数组（当前一期仅 0 有效）
|
||||||
|
preserve_style: mesh 管道专用，是否走阶段 3 风格还原
|
||||||
|
|
||||||
Returns:
|
Returns:
|
||||||
|
统一字段（不同管道可能缺省）：
|
||||||
{
|
{
|
||||||
"success": bool,
|
"success": bool,
|
||||||
"images": [{"url": str, "azimuth": int, "elevation": int}, ...],
|
"images": [{"url": str, "azimuth": int, "elevation": int}, ...],
|
||||||
"grid_image": str, # 原始拼接图的本地 URL
|
"grid_image": str | None, # grid 管道：原始拼接图 URL
|
||||||
|
"mesh_url": str | None, # mesh 管道：.glb URL
|
||||||
|
"color_video": str | None, # mesh 管道：360° color video URL
|
||||||
|
"normal_video": str | None, # mesh 管道：法线 video URL
|
||||||
|
"pipeline": "grid" | "mesh",
|
||||||
"model_name": str,
|
"model_name": str,
|
||||||
"error": str | None,
|
"error": str | None,
|
||||||
}
|
}
|
||||||
"""
|
"""
|
||||||
config = get_view_transform_model_config(model_id)
|
config = get_view_transform_model_config(model_id)
|
||||||
|
pipeline = config.get("pipeline", "grid")
|
||||||
|
|
||||||
|
GENERATED_DIR.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
|
if pipeline == "mesh":
|
||||||
|
return await _transform_view_mesh(
|
||||||
|
image_path=image_path,
|
||||||
|
config=config,
|
||||||
|
azimuths=azimuths,
|
||||||
|
elevations=elevations,
|
||||||
|
preserve_style=preserve_style,
|
||||||
|
)
|
||||||
|
|
||||||
|
return await _transform_view_grid(image_path=image_path, config=config)
|
||||||
|
|
||||||
|
|
||||||
|
async def _transform_view_grid(
|
||||||
|
image_path: str,
|
||||||
|
config: dict[str, Any],
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
"""原 Zero123++ 逻辑：单次调用 → grid 图 → 切 6 张。"""
|
||||||
model_name = config["name"]
|
model_name = config["name"]
|
||||||
replicate_model_id = config["model_id"]
|
replicate_model_id = config["model_id"]
|
||||||
grid_layout = config["grid_layout"]
|
grid_layout = config["grid_layout"]
|
||||||
output_views = config["output_views"]
|
output_views = config["output_views"]
|
||||||
|
|
||||||
GENERATED_DIR.mkdir(parents=True, exist_ok=True)
|
|
||||||
|
|
||||||
try:
|
try:
|
||||||
image_uri = to_data_uri(image_path)
|
image_uri = to_data_uri(image_path)
|
||||||
input_params = {"image": image_uri}
|
input_params = {"image": image_uri}
|
||||||
@@ -141,6 +199,10 @@ async def transform_view(
|
|||||||
"success": True,
|
"success": True,
|
||||||
"images": view_images,
|
"images": view_images,
|
||||||
"grid_image": grid_local_url,
|
"grid_image": grid_local_url,
|
||||||
|
"mesh_url": None,
|
||||||
|
"color_video": None,
|
||||||
|
"normal_video": None,
|
||||||
|
"pipeline": "grid",
|
||||||
"model_name": model_name,
|
"model_name": model_name,
|
||||||
"error": None,
|
"error": None,
|
||||||
}
|
}
|
||||||
@@ -152,6 +214,144 @@ async def transform_view(
|
|||||||
"success": False,
|
"success": False,
|
||||||
"images": [],
|
"images": [],
|
||||||
"grid_image": None,
|
"grid_image": None,
|
||||||
|
"mesh_url": None,
|
||||||
|
"color_video": None,
|
||||||
|
"normal_video": None,
|
||||||
|
"pipeline": "grid",
|
||||||
"model_name": model_name,
|
"model_name": model_name,
|
||||||
"error": detail,
|
"error": detail,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
async def _transform_view_mesh(
|
||||||
|
image_path: str,
|
||||||
|
config: dict[str, Any],
|
||||||
|
azimuths: list[int] | None,
|
||||||
|
elevations: list[int] | None,
|
||||||
|
preserve_style: bool,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
"""Mesh 管道调度器：阶段 1 生成 mesh + video；阶段 2/3 后续 Phase 接入。
|
||||||
|
|
||||||
|
Phase 1 验收状态：只跑阶段 1，返回 .glb / color_video / normal_video 本地 URL，
|
||||||
|
images 列表为空。Phase 2 完成后会填充 images（raw 抽帧结果），
|
||||||
|
Phase 3 完成后 images 会是经 IP-Adapter+ControlNet 重绘的最终图。
|
||||||
|
"""
|
||||||
|
model_name = config["name"]
|
||||||
|
model_id = config["id"]
|
||||||
|
|
||||||
|
# === Stage 1：生成 mesh + 预渲染视频 ===
|
||||||
|
stage1 = await mesh_generator.generate_mesh(image_path, model_id=model_id)
|
||||||
|
if not stage1.get("success"):
|
||||||
|
return {
|
||||||
|
"success": False,
|
||||||
|
"images": [],
|
||||||
|
"grid_image": None,
|
||||||
|
"mesh_url": None,
|
||||||
|
"color_video": None,
|
||||||
|
"normal_video": None,
|
||||||
|
"combined_video": None,
|
||||||
|
"pipeline": "mesh",
|
||||||
|
"model_name": model_name,
|
||||||
|
"error": stage1.get("error") or "阶段 1 失败",
|
||||||
|
}
|
||||||
|
|
||||||
|
# === Stage 2：抽帧 + 切左右半（color + normal）===
|
||||||
|
# azimuths / elevations 缺省时用默认 6 视角；长度对齐
|
||||||
|
if not azimuths:
|
||||||
|
azimuths = list(DEFAULT_MESH_AZIMUTHS)
|
||||||
|
if elevations is None or not elevations:
|
||||||
|
elevations = [0] * len(azimuths)
|
||||||
|
elif len(elevations) < len(azimuths):
|
||||||
|
elevations = list(elevations) + [0] * (len(azimuths) - len(elevations))
|
||||||
|
elif len(elevations) > len(azimuths):
|
||||||
|
elevations = list(elevations[: len(azimuths)])
|
||||||
|
|
||||||
|
# 优先 color_video（当前 Trellis 部署版恒为 None），缺则 fallback 到 combined_video
|
||||||
|
combined_video_path = stage1.get("combined_video_path")
|
||||||
|
frames: list[dict[str, Any]] = []
|
||||||
|
stage2_error: str | None = None
|
||||||
|
if combined_video_path:
|
||||||
|
try:
|
||||||
|
frames = await video_frame_extractor.extract_by_azimuth(
|
||||||
|
combined_video_path=combined_video_path,
|
||||||
|
azimuths=azimuths,
|
||||||
|
elevations=elevations,
|
||||||
|
total_rotation_deg=360,
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
stage2_error = f"Stage 2 抽帧失败：{e}"
|
||||||
|
logger.error(stage2_error, exc_info=True)
|
||||||
|
else:
|
||||||
|
stage2_error = "Trellis 未返回 combined_video，无法执行 Stage 2 抽帧"
|
||||||
|
logger.error(stage2_error)
|
||||||
|
|
||||||
|
# === Stage 3：风格还原（可选）===
|
||||||
|
# preserve_style=True 时对每一帧的 normal_png 做 IP-Adapter+ControlNet 重绘，
|
||||||
|
# 用户原图做风格参考；失败的单帧会回退为 Stage 2 的 color 帧，不阻塞其它帧。
|
||||||
|
stage3_error: str | None = None
|
||||||
|
stage3_results: list[dict[str, Any]] = []
|
||||||
|
did_stage3 = bool(preserve_style) and bool(frames)
|
||||||
|
if did_stage3:
|
||||||
|
try:
|
||||||
|
stage3_results = await style_restorer.restore_batch(
|
||||||
|
original_image=image_path,
|
||||||
|
frames=frames,
|
||||||
|
concurrency=3,
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
stage3_error = f"Stage 3 风格还原失败：{e}"
|
||||||
|
logger.error(stage3_error, exc_info=True)
|
||||||
|
|
||||||
|
# 组装最终 images：
|
||||||
|
# - Stage 3 成功的帧 → 用重绘后的 URL
|
||||||
|
# - Stage 3 失败 / 未跑 → 回退到 Stage 2 的 color 帧（保证前端至少能看到点东西）
|
||||||
|
images: list[dict[str, Any]] = []
|
||||||
|
for i, f in enumerate(frames):
|
||||||
|
restyled = stage3_results[i] if i < len(stage3_results) else None
|
||||||
|
if restyled and restyled.get("success") and restyled.get("url"):
|
||||||
|
final_url = restyled["url"]
|
||||||
|
frame_error = None
|
||||||
|
else:
|
||||||
|
final_url = f["color_png"]
|
||||||
|
frame_error = (restyled or {}).get("error") if did_stage3 else None
|
||||||
|
images.append({
|
||||||
|
"url": final_url,
|
||||||
|
"azimuth": f["az"],
|
||||||
|
"elevation": f["el"],
|
||||||
|
"normal_url": f["normal_png"],
|
||||||
|
"color_url": f["color_png"],
|
||||||
|
"frame_idx": f["frame_idx"],
|
||||||
|
"restyled": bool(restyled and restyled.get("success")),
|
||||||
|
**({"restyle_error": frame_error} if frame_error else {}),
|
||||||
|
})
|
||||||
|
|
||||||
|
# Stage 2 失败不把整体置为失败——Stage 1 的 mesh / video 产物仍有交付价值
|
||||||
|
# Stage 3 部分失败也不置为整体失败（每帧都有 Stage 2 回退）
|
||||||
|
success = bool(stage1.get("success")) and (stage2_error is None)
|
||||||
|
|
||||||
|
# 合并错误信息（Stage 2 和 Stage 3 错误都要暴露给前端）
|
||||||
|
error_parts = [e for e in (stage2_error, stage3_error) if e]
|
||||||
|
error_out = "; ".join(error_parts) if error_parts else None
|
||||||
|
|
||||||
|
if did_stage3:
|
||||||
|
restyled_ok = sum(1 for img in images if img.get("restyled"))
|
||||||
|
stage_label = f"stage3 ({restyled_ok}/{len(images)} restyled)"
|
||||||
|
elif frames:
|
||||||
|
stage_label = "stage2"
|
||||||
|
else:
|
||||||
|
stage_label = "stage1"
|
||||||
|
|
||||||
|
return {
|
||||||
|
"success": success,
|
||||||
|
"images": images,
|
||||||
|
"grid_image": None,
|
||||||
|
"mesh_url": stage1.get("glb_path"),
|
||||||
|
"color_video": stage1.get("color_video_path"),
|
||||||
|
"normal_video": stage1.get("normal_video_path"),
|
||||||
|
"combined_video": combined_video_path,
|
||||||
|
"pipeline": "mesh",
|
||||||
|
"model_name": model_name,
|
||||||
|
"error": error_out,
|
||||||
|
"_stage": stage_label,
|
||||||
|
"_preserve_style_requested": bool(preserve_style),
|
||||||
|
}
|
||||||
|
|||||||
Binary file not shown.
@@ -1,5 +1,6 @@
|
|||||||
fastapi==0.135.3
|
fastapi==0.135.3
|
||||||
uvicorn==0.44.0
|
uvicorn==0.44.0
|
||||||
|
watchfiles==0.24.0
|
||||||
openai==2.32.0
|
openai==2.32.0
|
||||||
replicate==1.0.7
|
replicate==1.0.7
|
||||||
sse-starlette==3.3.4
|
sse-starlette==3.3.4
|
||||||
@@ -7,6 +8,7 @@ python-multipart==0.0.26
|
|||||||
httpx==0.28.1
|
httpx==0.28.1
|
||||||
python-dotenv==1.2.2
|
python-dotenv==1.2.2
|
||||||
Pillow==12.2.0
|
Pillow==12.2.0
|
||||||
|
imageio-ffmpeg==0.5.1
|
||||||
mem0ai==1.0.11
|
mem0ai==1.0.11
|
||||||
ollama==0.6.1
|
ollama==0.6.1
|
||||||
sqlmodel==0.0.38
|
sqlmodel==0.0.38
|
||||||
|
|||||||
107
art-agent/backend/scripts/test_frame_extract.py
Normal file
107
art-agent/backend/scripts/test_frame_extract.py
Normal file
@@ -0,0 +1,107 @@
|
|||||||
|
"""Phase 2 验收脚本：独立验证 combined_video 抽帧 + 左右切分逻辑。
|
||||||
|
|
||||||
|
不需要再跑一次 Trellis（省钱），直接用 generated/ 下已有的
|
||||||
|
`trellis_combined_*.mp4` 做验证。
|
||||||
|
|
||||||
|
用法（在 backend 目录激活 venv 之后）：
|
||||||
|
python scripts/test_frame_extract.py
|
||||||
|
python scripts/test_frame_extract.py generated/trellis_combined_211176d3940b.mp4
|
||||||
|
|
||||||
|
成功标准：
|
||||||
|
- 退出码 0
|
||||||
|
- 打印的 color_png / normal_png 均为 /generated/view_xxx.png
|
||||||
|
- 到 backend/generated/ 能看到 6 对 color + normal 文件（12 张）且尺寸接近正方形
|
||||||
|
- 目视检查：每组 color 图按 0/60/120/180/240/300° 依次环绕建筑一圈
|
||||||
|
"""
|
||||||
|
|
||||||
|
import asyncio
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
_BACKEND_ROOT = Path(__file__).resolve().parent.parent
|
||||||
|
if str(_BACKEND_ROOT) not in sys.path:
|
||||||
|
sys.path.insert(0, str(_BACKEND_ROOT))
|
||||||
|
|
||||||
|
from dotenv import load_dotenv # noqa: E402
|
||||||
|
|
||||||
|
load_dotenv(_BACKEND_ROOT / ".env", override=True)
|
||||||
|
|
||||||
|
from app.services import video_frame_extractor # noqa: E402
|
||||||
|
from app.services.image_gen import GENERATED_DIR # noqa: E402
|
||||||
|
|
||||||
|
|
||||||
|
def _pick_default_video() -> str:
|
||||||
|
candidates = sorted(
|
||||||
|
GENERATED_DIR.glob("trellis_combined_*.mp4"),
|
||||||
|
key=lambda p: p.stat().st_mtime,
|
||||||
|
reverse=True,
|
||||||
|
)
|
||||||
|
if not candidates:
|
||||||
|
raise FileNotFoundError(
|
||||||
|
"generated/ 下找不到 trellis_combined_*.mp4；请先跑一次 Phase 1 "
|
||||||
|
"（scripts/test_trellis.py）或显式传入视频路径"
|
||||||
|
)
|
||||||
|
return f"/generated/{candidates[0].name}"
|
||||||
|
|
||||||
|
|
||||||
|
async def main() -> int:
|
||||||
|
video_arg = sys.argv[1] if len(sys.argv) > 1 else _pick_default_video()
|
||||||
|
# 允许传相对路径或纯文件名
|
||||||
|
if not video_arg.startswith("/generated/"):
|
||||||
|
if video_arg.startswith("generated/"):
|
||||||
|
video_arg = "/" + video_arg.replace("\\", "/")
|
||||||
|
elif not video_arg.startswith("/") and not Path(video_arg).is_absolute():
|
||||||
|
# 如果只给了个文件名，假定在 generated/ 下
|
||||||
|
if (GENERATED_DIR / video_arg).exists():
|
||||||
|
video_arg = f"/generated/{video_arg}"
|
||||||
|
|
||||||
|
print(f"[test_frame_extract] 输入视频：{video_arg}")
|
||||||
|
print("[test_frame_extract] 抽取 6 视角：az=[0,60,120,180,240,300]，el 全 0")
|
||||||
|
|
||||||
|
azimuths = [0, 60, 120, 180, 240, 300]
|
||||||
|
elevations = [0] * len(azimuths)
|
||||||
|
|
||||||
|
frames = await video_frame_extractor.extract_by_azimuth(
|
||||||
|
combined_video_path=video_arg,
|
||||||
|
azimuths=azimuths,
|
||||||
|
elevations=elevations,
|
||||||
|
total_rotation_deg=360,
|
||||||
|
)
|
||||||
|
|
||||||
|
print("[test_frame_extract] 抽帧结果：")
|
||||||
|
print(json.dumps(frames, ensure_ascii=False, indent=2))
|
||||||
|
|
||||||
|
# 简单完整性校验
|
||||||
|
all_exist = True
|
||||||
|
for f in frames:
|
||||||
|
for key in ("color_png", "normal_png"):
|
||||||
|
rel = f.get(key)
|
||||||
|
if not rel:
|
||||||
|
print(f"[test_frame_extract] 警告：帧 az={f['az']} 缺少 {key}")
|
||||||
|
all_exist = False
|
||||||
|
continue
|
||||||
|
local = GENERATED_DIR / Path(rel).name
|
||||||
|
size = local.stat().st_size if local.exists() else -1
|
||||||
|
status = "OK" if size > 0 else "MISSING"
|
||||||
|
print(f" [{status}] az={f['az']:3d} {key}: {rel} ({size} bytes)")
|
||||||
|
if size <= 0:
|
||||||
|
all_exist = False
|
||||||
|
|
||||||
|
if not all_exist:
|
||||||
|
print("[test_frame_extract] 部分文件缺失，判定失败")
|
||||||
|
return 1
|
||||||
|
|
||||||
|
print(
|
||||||
|
f"[test_frame_extract] 成功：共 {len(frames)} 个视角，"
|
||||||
|
f"color+normal 合计 {len(frames) * 2} 张已落盘到 {GENERATED_DIR}"
|
||||||
|
)
|
||||||
|
print(
|
||||||
|
"[test_frame_extract] 请目视检查：打开 generated/ 下任意 view_*_color.png，"
|
||||||
|
"确认 az=0 正面、az=180 背面、其余按顺序环绕；normal 帧应为蓝紫调法线图。"
|
||||||
|
)
|
||||||
|
return 0
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
sys.exit(asyncio.run(main()))
|
||||||
167
art-agent/backend/scripts/test_style_restore.py
Normal file
167
art-agent/backend/scripts/test_style_restore.py
Normal file
@@ -0,0 +1,167 @@
|
|||||||
|
"""Phase 3 / Checkpoint 3 验收脚本：独立验证 Stage 3 风格还原链路。
|
||||||
|
|
||||||
|
复用 Phase 2 已抽出的 normal 帧，无需再跑 Trellis（省 $0.041）。
|
||||||
|
默认会挑最新一组 view_*_el0_normal.png 作为结构参考，并让用户指定原图。
|
||||||
|
|
||||||
|
用法（在 backend 目录激活 venv 后）：
|
||||||
|
# 1. 全 6 帧批量重绘（~6 × $0.07 ≈ $0.42）
|
||||||
|
python scripts/test_style_restore.py <原图路径>
|
||||||
|
|
||||||
|
# 2. 只跑一帧做快速冒烟（便宜 ~$0.07）
|
||||||
|
python scripts/test_style_restore.py <原图路径> --single
|
||||||
|
|
||||||
|
# 3. 手动指定 normal 帧前缀（不指定时用最新一组）
|
||||||
|
python scripts/test_style_restore.py <原图路径> --prefix view_xxxxxxxx
|
||||||
|
|
||||||
|
成功标准：
|
||||||
|
- 退出码 0
|
||||||
|
- 打印的每一帧都返回 success=True 且 url 以 /generated/restyled_ 开头
|
||||||
|
- 打开 generated/restyled_* 图片，目视检查：风格与原图一致、视角符合 az 标注
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import asyncio
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
_BACKEND_ROOT = Path(__file__).resolve().parent.parent
|
||||||
|
if str(_BACKEND_ROOT) not in sys.path:
|
||||||
|
sys.path.insert(0, str(_BACKEND_ROOT))
|
||||||
|
|
||||||
|
from dotenv import load_dotenv # noqa: E402
|
||||||
|
|
||||||
|
load_dotenv(_BACKEND_ROOT / ".env", override=True)
|
||||||
|
|
||||||
|
from app.services import style_restorer # noqa: E402
|
||||||
|
from app.services.image_gen import GENERATED_DIR # noqa: E402
|
||||||
|
|
||||||
|
|
||||||
|
def _pick_latest_normal_group() -> tuple[str, list[dict]]:
|
||||||
|
"""在 generated/ 下挑一组最新的 view_<prefix>_az*_el0_normal.png，按 az 排好序。
|
||||||
|
|
||||||
|
返回 (prefix, frames)，frames = [{az, el, normal_png, color_png}, ...]
|
||||||
|
"""
|
||||||
|
all_normals = sorted(
|
||||||
|
GENERATED_DIR.glob("view_*_el0_normal.png"),
|
||||||
|
key=lambda p: p.stat().st_mtime,
|
||||||
|
reverse=True,
|
||||||
|
)
|
||||||
|
if not all_normals:
|
||||||
|
raise FileNotFoundError(
|
||||||
|
"generated/ 下找不到 view_*_el0_normal.png；请先跑 scripts/test_frame_extract.py"
|
||||||
|
)
|
||||||
|
# 最新文件的 prefix：view_<8hex>_az...
|
||||||
|
latest_name = all_normals[0].name
|
||||||
|
# 形如 view_63731b77_az0_el0_normal.png → prefix = view_63731b77
|
||||||
|
parts = latest_name.split("_")
|
||||||
|
prefix = "_".join(parts[:2])
|
||||||
|
return prefix, _load_group_by_prefix(prefix)
|
||||||
|
|
||||||
|
|
||||||
|
def _load_group_by_prefix(prefix: str) -> list[dict]:
|
||||||
|
normals = sorted(GENERATED_DIR.glob(f"{prefix}_az*_el0_normal.png"))
|
||||||
|
if not normals:
|
||||||
|
raise FileNotFoundError(f"找不到前缀为 {prefix} 的 normal 帧")
|
||||||
|
frames = []
|
||||||
|
for n in normals:
|
||||||
|
# 从文件名解析 az：view_63731b77_az120_el0_normal.png → az=120
|
||||||
|
tokens = n.stem.split("_")
|
||||||
|
az = 0
|
||||||
|
el = 0
|
||||||
|
for t in tokens:
|
||||||
|
if t.startswith("az"):
|
||||||
|
try:
|
||||||
|
az = int(t[2:])
|
||||||
|
except ValueError:
|
||||||
|
pass
|
||||||
|
elif t.startswith("el"):
|
||||||
|
try:
|
||||||
|
el = int(t[2:])
|
||||||
|
except ValueError:
|
||||||
|
pass
|
||||||
|
color = n.with_name(n.name.replace("_normal.png", "_color.png"))
|
||||||
|
frames.append({
|
||||||
|
"az": az,
|
||||||
|
"el": el,
|
||||||
|
"normal_png": f"/generated/{n.name}",
|
||||||
|
"color_png": f"/generated/{color.name}" if color.exists() else None,
|
||||||
|
"frame_idx": -1,
|
||||||
|
})
|
||||||
|
frames.sort(key=lambda f: f["az"])
|
||||||
|
return frames
|
||||||
|
|
||||||
|
|
||||||
|
async def main() -> int:
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument("original", help="用户原图路径（本地相对/绝对路径均可）")
|
||||||
|
parser.add_argument("--prefix", default=None, help="normal 帧的文件名前缀（如 view_63731b77）")
|
||||||
|
parser.add_argument("--single", action="store_true", help="只跑第一帧做快速冒烟")
|
||||||
|
parser.add_argument("--scale", type=float, default=None, help="覆盖 IP-Adapter 权重（0-1）")
|
||||||
|
parser.add_argument("--cn-scale", type=float, default=None, help="覆盖 ControlNet 权重（0-1）")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
original = args.original
|
||||||
|
original_path = Path(original)
|
||||||
|
if not original_path.is_absolute():
|
||||||
|
original_path = (_BACKEND_ROOT / original).resolve()
|
||||||
|
if not original_path.exists():
|
||||||
|
print(f"[test_style_restore] 原图不存在：{original_path}")
|
||||||
|
return 2
|
||||||
|
|
||||||
|
if args.prefix:
|
||||||
|
frames = _load_group_by_prefix(args.prefix)
|
||||||
|
prefix = args.prefix
|
||||||
|
else:
|
||||||
|
prefix, frames = _pick_latest_normal_group()
|
||||||
|
|
||||||
|
if args.single:
|
||||||
|
frames = frames[:1]
|
||||||
|
|
||||||
|
override_params = {}
|
||||||
|
if args.scale is not None:
|
||||||
|
override_params["scale"] = args.scale
|
||||||
|
if args.cn_scale is not None:
|
||||||
|
override_params["controlnet_conditioning_scale"] = args.cn_scale
|
||||||
|
|
||||||
|
print(f"[test_style_restore] 原图：{original_path}")
|
||||||
|
print(f"[test_style_restore] normal 帧组 prefix={prefix}，共 {len(frames)} 帧")
|
||||||
|
print(f"[test_style_restore] 角度列表：{[f['az'] for f in frames]}")
|
||||||
|
if override_params:
|
||||||
|
print(f"[test_style_restore] 覆盖参数：{override_params}")
|
||||||
|
print(
|
||||||
|
f"[test_style_restore] 预计耗时 ~{72}s × {len(frames)}，"
|
||||||
|
f"成本 ~${0.07 * len(frames):.2f}（并发 3 实际会更快）"
|
||||||
|
)
|
||||||
|
|
||||||
|
results = await style_restorer.restore_batch(
|
||||||
|
original_image=str(original_path),
|
||||||
|
frames=frames,
|
||||||
|
params=override_params or None,
|
||||||
|
concurrency=3,
|
||||||
|
)
|
||||||
|
|
||||||
|
print("[test_style_restore] 重绘结果：")
|
||||||
|
print(json.dumps(results, ensure_ascii=False, indent=2))
|
||||||
|
|
||||||
|
ok = sum(1 for r in results if r.get("success"))
|
||||||
|
print(f"[test_style_restore] 成功 {ok}/{len(results)} 帧")
|
||||||
|
|
||||||
|
if ok == 0:
|
||||||
|
print("[test_style_restore] 全军覆没，判定失败")
|
||||||
|
return 1
|
||||||
|
if ok < len(results):
|
||||||
|
print("[test_style_restore] 部分帧失败，视为部分通过；请检查上方错误信息")
|
||||||
|
return 0
|
||||||
|
|
||||||
|
print(
|
||||||
|
"[test_style_restore] 全部成功；请目视检查 generated/restyled_* 图片："
|
||||||
|
"风格应贴近原图、视角按 az 顺序环绕。"
|
||||||
|
)
|
||||||
|
return 0
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
sys.exit(asyncio.run(main()))
|
||||||
72
art-agent/backend/scripts/test_trellis.py
Normal file
72
art-agent/backend/scripts/test_trellis.py
Normal file
@@ -0,0 +1,72 @@
|
|||||||
|
"""Phase 1 验收脚本：直接调用 Trellis，验证 .glb + color_video + normal_video 能下到本地。
|
||||||
|
|
||||||
|
用法（在 backend 目录激活 venv 之后）：
|
||||||
|
python scripts/test_trellis.py uploads/0e6fd7e47a524bb9ad18de0b72495e0e.png
|
||||||
|
|
||||||
|
不带参数时会尝试使用 uploads/ 下最新的 png 作为测试图。
|
||||||
|
|
||||||
|
成功标准：
|
||||||
|
- 退出码 0
|
||||||
|
- 终端打印 glb_path / color_video_path / normal_video_path 均为 /generated/ 开头
|
||||||
|
- 实际到 backend/generated/ 目录能看到 3 个文件且 size > 0
|
||||||
|
"""
|
||||||
|
|
||||||
|
import asyncio
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# 允许直接 `python scripts/test_trellis.py` 跑
|
||||||
|
_BACKEND_ROOT = Path(__file__).resolve().parent.parent
|
||||||
|
if str(_BACKEND_ROOT) not in sys.path:
|
||||||
|
sys.path.insert(0, str(_BACKEND_ROOT))
|
||||||
|
|
||||||
|
# .env 加载（复用项目 main.py 的习惯）
|
||||||
|
from dotenv import load_dotenv # noqa: E402
|
||||||
|
|
||||||
|
load_dotenv(_BACKEND_ROOT / ".env", override=True)
|
||||||
|
|
||||||
|
from app.services import mesh_generator # noqa: E402
|
||||||
|
|
||||||
|
|
||||||
|
def _pick_default_image() -> str:
|
||||||
|
uploads = _BACKEND_ROOT / "uploads"
|
||||||
|
pngs = sorted(uploads.glob("*.png"), key=lambda p: p.stat().st_mtime, reverse=True)
|
||||||
|
if not pngs:
|
||||||
|
raise FileNotFoundError(f"uploads/ 下没有 png 文件，请显式传入图片路径")
|
||||||
|
return str(pngs[0].relative_to(_BACKEND_ROOT)).replace("\\", "/")
|
||||||
|
|
||||||
|
|
||||||
|
async def main() -> int:
|
||||||
|
image_arg = sys.argv[1] if len(sys.argv) > 1 else _pick_default_image()
|
||||||
|
# 规范化成 / 开头的 "本地相对 URL" 以便 to_data_uri 识别
|
||||||
|
if not image_arg.startswith("/") and not image_arg.startswith("data:") and not image_arg.startswith("http"):
|
||||||
|
image_arg = "/" + image_arg.lstrip("./").replace("\\", "/")
|
||||||
|
|
||||||
|
print(f"[test_trellis] 输入图：{image_arg}")
|
||||||
|
print("[test_trellis] 开始调用 Trellis（预计 ~30s 起）...")
|
||||||
|
|
||||||
|
result = await mesh_generator.generate_with_trellis(image_arg)
|
||||||
|
|
||||||
|
print("[test_trellis] Trellis 返回：")
|
||||||
|
print(json.dumps(result, ensure_ascii=False, indent=2))
|
||||||
|
|
||||||
|
if not result.get("success"):
|
||||||
|
print("[test_trellis] 失败：", result.get("error"))
|
||||||
|
return 1
|
||||||
|
|
||||||
|
generated_dir = _BACKEND_ROOT / "generated"
|
||||||
|
for key in ("glb_path", "color_video_path", "normal_video_path"):
|
||||||
|
rel = result.get(key)
|
||||||
|
if not rel:
|
||||||
|
print(f"[test_trellis] 警告：缺少 {key}")
|
||||||
|
continue
|
||||||
|
local = generated_dir / Path(rel).name
|
||||||
|
size = local.stat().st_size if local.exists() else -1
|
||||||
|
print(f"[test_trellis] {key}: {rel} (本地大小: {size} bytes)")
|
||||||
|
|
||||||
|
return 0
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
sys.exit(asyncio.run(main()))
|
||||||
1502
art-agent/frontend/package-lock.json
generated
1502
art-agent/frontend/package-lock.json
generated
File diff suppressed because it is too large
Load Diff
@@ -12,7 +12,9 @@
|
|||||||
"framer-motion": "^12.38.0",
|
"framer-motion": "^12.38.0",
|
||||||
"next": "^15.1.0",
|
"next": "^15.1.0",
|
||||||
"react": "^19.0.0",
|
"react": "^19.0.0",
|
||||||
"react-dom": "^19.0.0"
|
"react-dom": "^19.0.0",
|
||||||
|
"react-markdown": "^10.1.0",
|
||||||
|
"remark-gfm": "^4.0.1"
|
||||||
},
|
},
|
||||||
"devDependencies": {
|
"devDependencies": {
|
||||||
"@tailwindcss/postcss": "^4.0.0",
|
"@tailwindcss/postcss": "^4.0.0",
|
||||||
|
|||||||
254
art-agent/frontend/src/app/docs/page.tsx
Normal file
254
art-agent/frontend/src/app/docs/page.tsx
Normal file
@@ -0,0 +1,254 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useState, useEffect, useMemo } from "react";
|
||||||
|
import { TopNav } from "@/components/layout/top-nav";
|
||||||
|
import { AmbientParticles } from "@/components/ui/ambient-particles";
|
||||||
|
import { DocTree } from "@/components/docs/doc-tree";
|
||||||
|
import { DocTabs } from "@/components/docs/doc-tabs";
|
||||||
|
import { DocEditor } from "@/components/docs/doc-editor";
|
||||||
|
import { DocOutline } from "@/components/docs/doc-outline";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import type { DocNode } from "@/lib/types";
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 文档管理中心（Phase 1）
|
||||||
|
*
|
||||||
|
* 三栏布局：
|
||||||
|
* - 左：文档树（文件夹 + 文档，右键菜单、拖拽移动、搜索）
|
||||||
|
* - 中：多 Tab 编辑器（Markdown 源码 / 分栏 / 预览）
|
||||||
|
* - 右：大纲 + 关联资产 + AI 助手入口
|
||||||
|
*/
|
||||||
|
export default function DocsPage() {
|
||||||
|
const { docs, updateDocContent } = useApp();
|
||||||
|
|
||||||
|
// 打开的 Tab 列表（按顺序）
|
||||||
|
const [openIds, setOpenIds] = useState<string[]>([]);
|
||||||
|
const [activeId, setActiveId] = useState<string | null>(null);
|
||||||
|
/** 每个 Tab 的未保存 buffer（nodeId -> content）。无条目表示已同步。 */
|
||||||
|
const [buffers, setBuffers] = useState<Record<string, string>>({});
|
||||||
|
const [treeSearch, setTreeSearch] = useState("");
|
||||||
|
const [showTree, setShowTree] = useState(true);
|
||||||
|
const [showOutline, setShowOutline] = useState(true);
|
||||||
|
|
||||||
|
// 在 docs 列表中递归查找节点
|
||||||
|
const findNode = (list: DocNode[], id: string): DocNode | null => {
|
||||||
|
for (const n of list) {
|
||||||
|
if (n.id === id) return n;
|
||||||
|
if (n.children) {
|
||||||
|
const r = findNode(n.children, id);
|
||||||
|
if (r) return r;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return null;
|
||||||
|
};
|
||||||
|
|
||||||
|
// 自动打开第一个有内容的文档
|
||||||
|
useEffect(() => {
|
||||||
|
if (openIds.length === 0 && docs.length > 0) {
|
||||||
|
const findFirstDoc = (list: DocNode[]): DocNode | null => {
|
||||||
|
for (const n of list) {
|
||||||
|
if (n.type === "doc") return n;
|
||||||
|
if (n.children) {
|
||||||
|
const r = findFirstDoc(n.children);
|
||||||
|
if (r) return r;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return null;
|
||||||
|
};
|
||||||
|
const first = findFirstDoc(docs);
|
||||||
|
if (first) {
|
||||||
|
setOpenIds([first.id]);
|
||||||
|
setActiveId(first.id);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}, [docs, openIds.length]);
|
||||||
|
|
||||||
|
const openTabs = useMemo(
|
||||||
|
() =>
|
||||||
|
openIds
|
||||||
|
.map((id) => {
|
||||||
|
const node = findNode(docs, id);
|
||||||
|
if (!node) return null;
|
||||||
|
const dirty = buffers[id] !== undefined && buffers[id] !== (node.content ?? "");
|
||||||
|
return { node, dirty };
|
||||||
|
})
|
||||||
|
.filter((x): x is { node: DocNode; dirty: boolean } => x !== null),
|
||||||
|
[openIds, docs, buffers]
|
||||||
|
);
|
||||||
|
|
||||||
|
const openDoc = (node: DocNode) => {
|
||||||
|
if (node.type !== "doc") return;
|
||||||
|
setOpenIds((prev) => (prev.includes(node.id) ? prev : [...prev, node.id]));
|
||||||
|
setActiveId(node.id);
|
||||||
|
};
|
||||||
|
|
||||||
|
const closeTab = (id: string) => {
|
||||||
|
setOpenIds((prev) => {
|
||||||
|
const idx = prev.indexOf(id);
|
||||||
|
if (idx < 0) return prev;
|
||||||
|
// 若有 dirty 且未保存，简单 confirm
|
||||||
|
const dirty = buffers[id] !== undefined && buffers[id] !== (findNode(docs, id)?.content ?? "");
|
||||||
|
if (dirty && !confirm("存在未保存的修改，确认关闭？")) return prev;
|
||||||
|
const next = prev.filter((x) => x !== id);
|
||||||
|
if (activeId === id) {
|
||||||
|
setActiveId(next[Math.min(idx, next.length - 1)] ?? null);
|
||||||
|
}
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
setBuffers((prev) => {
|
||||||
|
const { [id]: _, ...rest } = prev;
|
||||||
|
return rest;
|
||||||
|
});
|
||||||
|
};
|
||||||
|
|
||||||
|
const closeOthers = (keepId: string) => {
|
||||||
|
setOpenIds((prev) => prev.filter((id) => id === keepId));
|
||||||
|
setActiveId(keepId);
|
||||||
|
setBuffers((prev) => ({ keepId: prev[keepId], ...(prev[keepId] !== undefined ? { [keepId]: prev[keepId] } : {}) }));
|
||||||
|
};
|
||||||
|
|
||||||
|
const closeAll = () => {
|
||||||
|
if (Object.keys(buffers).length > 0 && !confirm("存在未保存的修改，确认关闭全部？")) return;
|
||||||
|
setOpenIds([]);
|
||||||
|
setActiveId(null);
|
||||||
|
setBuffers({});
|
||||||
|
};
|
||||||
|
|
||||||
|
const activeDoc = activeId ? findNode(docs, activeId) : null;
|
||||||
|
const activeBuffer =
|
||||||
|
activeDoc && activeId
|
||||||
|
? buffers[activeId] !== undefined
|
||||||
|
? buffers[activeId]
|
||||||
|
: activeDoc.content ?? ""
|
||||||
|
: "";
|
||||||
|
|
||||||
|
const handleContentChange = (content: string) => {
|
||||||
|
if (!activeId) return;
|
||||||
|
setBuffers((prev) => ({ ...prev, [activeId]: content }));
|
||||||
|
};
|
||||||
|
|
||||||
|
const handleSave = () => {
|
||||||
|
if (!activeId || !activeDoc) return;
|
||||||
|
const buf = buffers[activeId];
|
||||||
|
if (buf === undefined) return;
|
||||||
|
updateDocContent(activeId, buf);
|
||||||
|
setBuffers((prev) => {
|
||||||
|
const { [activeId]: _, ...rest } = prev;
|
||||||
|
return rest;
|
||||||
|
});
|
||||||
|
};
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="h-screen flex flex-col relative z-[1]">
|
||||||
|
<AmbientParticles count={12} />
|
||||||
|
<TopNav />
|
||||||
|
|
||||||
|
<div className="flex-1 flex overflow-hidden">
|
||||||
|
{/* 左栏：文档树 */}
|
||||||
|
{showTree && (
|
||||||
|
<aside className="w-56 md:w-64 flex-shrink-0 border-r border-[var(--border)]
|
||||||
|
bg-[var(--bg-secondary)]/40 backdrop-blur-sm flex flex-col">
|
||||||
|
<DocTree
|
||||||
|
activeId={activeId}
|
||||||
|
openIds={new Set(openIds)}
|
||||||
|
onOpen={openDoc}
|
||||||
|
searchQuery={treeSearch}
|
||||||
|
onSearch={setTreeSearch}
|
||||||
|
/>
|
||||||
|
</aside>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{/* 中栏：Tabs + 编辑器 */}
|
||||||
|
<main className="flex-1 flex flex-col min-w-0 bg-[var(--bg-primary)]">
|
||||||
|
{/* 折叠/展开按钮 */}
|
||||||
|
<div className="flex-shrink-0 flex items-center border-b border-[var(--border)] px-2 py-1 gap-1
|
||||||
|
bg-[var(--bg-secondary)]/50 backdrop-blur-sm">
|
||||||
|
<button
|
||||||
|
onClick={() => setShowTree(!showTree)}
|
||||||
|
className="p-1.5 rounded-md text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:bg-[var(--accent)]/5 cursor-pointer transition-colors"
|
||||||
|
title={showTree ? "隐藏文档树" : "显示文档树"}
|
||||||
|
>
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<line x1="9" y1="3" x2="9" y2="21" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)] flex items-center gap-1">
|
||||||
|
文档中心
|
||||||
|
<span className="phase-chip">P1</span>
|
||||||
|
</span>
|
||||||
|
<div className="flex-1" />
|
||||||
|
<button
|
||||||
|
onClick={() => setShowOutline(!showOutline)}
|
||||||
|
className="p-1.5 rounded-md text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:bg-[var(--accent)]/5 cursor-pointer transition-colors"
|
||||||
|
title={showOutline ? "隐藏大纲" : "显示大纲"}
|
||||||
|
>
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<line x1="15" y1="3" x2="15" y2="21" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<DocTabs
|
||||||
|
openTabs={openTabs}
|
||||||
|
activeId={activeId}
|
||||||
|
onActivate={setActiveId}
|
||||||
|
onClose={closeTab}
|
||||||
|
onCloseOthers={closeOthers}
|
||||||
|
onCloseAll={closeAll}
|
||||||
|
/>
|
||||||
|
|
||||||
|
{activeDoc ? (
|
||||||
|
<DocEditor
|
||||||
|
doc={activeDoc}
|
||||||
|
buffer={activeBuffer}
|
||||||
|
onChange={handleContentChange}
|
||||||
|
onSave={handleSave}
|
||||||
|
/>
|
||||||
|
) : (
|
||||||
|
<DocEmptyState />
|
||||||
|
)}
|
||||||
|
</main>
|
||||||
|
|
||||||
|
{/* 右栏：大纲 + 关联资产 */}
|
||||||
|
{showOutline && activeDoc && (
|
||||||
|
<aside className="w-56 md:w-64 flex-shrink-0 border-l border-[var(--border)]
|
||||||
|
bg-[var(--bg-secondary)]/40 backdrop-blur-sm">
|
||||||
|
<DocOutline content={activeBuffer} />
|
||||||
|
</aside>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function DocEmptyState() {
|
||||||
|
return (
|
||||||
|
<div className="flex-1 flex items-center justify-center">
|
||||||
|
<div className="text-center space-y-4 max-w-md px-6">
|
||||||
|
<div className="inline-flex items-center justify-center w-16 h-16 rounded-2xl
|
||||||
|
bg-[var(--accent)]/8 border border-[var(--accent)]/20">
|
||||||
|
<svg width="28" height="28" viewBox="0 0 24 24" fill="none" stroke="var(--accent)" strokeWidth="1.5" opacity="0.7">
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
<line x1="8" y1="13" x2="16" y2="13" />
|
||||||
|
<line x1="8" y1="17" x2="13" y2="17" />
|
||||||
|
</svg>
|
||||||
|
</div>
|
||||||
|
<div>
|
||||||
|
<p className="typo-display text-lg mb-2">文档管理中心</p>
|
||||||
|
<p className="typo-caption leading-relaxed">
|
||||||
|
在这里沉淀项目的世界观、角色档案、Prompt 模板与交付规范。<br />
|
||||||
|
从左侧选择一份文档开始，或按 <kbd className="px-1.5 py-0.5 rounded bg-[var(--bg-tertiary)] border border-[var(--border)] text-[10px] font-mono">Ctrl+K</kbd> 全局搜索。
|
||||||
|
</p>
|
||||||
|
</div>
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)]">
|
||||||
|
当前占位阶段：本地存储，真实云同步待 Phase 2。
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
@@ -1,14 +1,15 @@
|
|||||||
"use client";
|
"use client";
|
||||||
|
|
||||||
import { useState, useMemo } from "react";
|
import { useState, useMemo } from "react";
|
||||||
import { motion, AnimatePresence } from "framer-motion";
|
import { motion } from "framer-motion";
|
||||||
import { TopNav } from "@/components/layout/top-nav";
|
import { TopNav } from "@/components/layout/top-nav";
|
||||||
import { AmbientParticles } from "@/components/ui/ambient-particles";
|
import { AmbientParticles } from "@/components/ui/ambient-particles";
|
||||||
import { useFireflyBurst, FireflyBurst } from "@/components/ui/firefly-burst";
|
|
||||||
import { useApp } from "@/lib/app-context";
|
import { useApp } from "@/lib/app-context";
|
||||||
import { getImageUrl } from "@/lib/api";
|
import { getImageUrl } from "@/lib/api";
|
||||||
import { staggerContainer, staggerItem, slideUp } from "@/components/ui/motion-presets";
|
import { staggerContainer, staggerItem, slideUp } from "@/components/ui/motion-presets";
|
||||||
import type { ImageAsset } from "@/lib/types";
|
import { Model3DPanel } from "@/components/detail/model-3d-panel";
|
||||||
|
import { MotionPanel } from "@/components/detail/motion-panel";
|
||||||
|
import type { ImageAsset, Asset3D, AssetMotion, TaskType } from "@/lib/types";
|
||||||
|
|
||||||
type ViewMode = "grid" | "list";
|
type ViewMode = "grid" | "list";
|
||||||
type SortBy = "time" | "name";
|
type SortBy = "time" | "name";
|
||||||
@@ -23,8 +24,10 @@ const ASSET_TYPES = [
|
|||||||
];
|
];
|
||||||
|
|
||||||
export default function GalleryPage() {
|
export default function GalleryPage() {
|
||||||
const { assets, tags, toggleFavorite, deleteAssetById, stylePacks, characters } = useApp();
|
const { assets, tags, toggleFavorite, deleteAssetById, stylePacks, characters,
|
||||||
|
assets3D, assetsMotion, deleteAsset3D, deleteAssetMotion } = useApp();
|
||||||
|
|
||||||
|
const [modality, setModality] = useState<TaskType>("image2d");
|
||||||
const [viewMode, setViewMode] = useState<ViewMode>("grid");
|
const [viewMode, setViewMode] = useState<ViewMode>("grid");
|
||||||
const [sortBy, setSortBy] = useState<SortBy>("time");
|
const [sortBy, setSortBy] = useState<SortBy>("time");
|
||||||
const [selectedTagIds, setSelectedTagIds] = useState<string[]>([]);
|
const [selectedTagIds, setSelectedTagIds] = useState<string[]>([]);
|
||||||
@@ -33,6 +36,8 @@ export default function GalleryPage() {
|
|||||||
const [showFavOnly, setShowFavOnly] = useState(false);
|
const [showFavOnly, setShowFavOnly] = useState(false);
|
||||||
const [selectedIds, setSelectedIds] = useState<Set<string>>(new Set());
|
const [selectedIds, setSelectedIds] = useState<Set<string>>(new Set());
|
||||||
const [detailAsset, setDetailAsset] = useState<ImageAsset | null>(null);
|
const [detailAsset, setDetailAsset] = useState<ImageAsset | null>(null);
|
||||||
|
const [detail3D, setDetail3D] = useState<Asset3D | null>(null);
|
||||||
|
const [detailMotion, setDetailMotion] = useState<AssetMotion | null>(null);
|
||||||
const [selectedAssetType, setSelectedAssetType] = useState<string | null>(null);
|
const [selectedAssetType, setSelectedAssetType] = useState<string | null>(null);
|
||||||
const [selectedStyleId, setSelectedStyleId] = useState<string | null>(null);
|
const [selectedStyleId, setSelectedStyleId] = useState<string | null>(null);
|
||||||
const [selectedCharacterId, setSelectedCharacterId] = useState<string | null>(null);
|
const [selectedCharacterId, setSelectedCharacterId] = useState<string | null>(null);
|
||||||
@@ -161,8 +166,60 @@ export default function GalleryPage() {
|
|||||||
<AmbientParticles count={filtered.length === 0 ? 25 : 15} />
|
<AmbientParticles count={filtered.length === 0 ? 25 : 15} />
|
||||||
<TopNav />
|
<TopNav />
|
||||||
|
|
||||||
|
{/* 资产类型 Tab（2D 图片 / 3D 模型 / 动作序列） */}
|
||||||
|
<div className="flex-shrink-0 border-b border-[var(--border)] surface-1 px-4 md:px-5">
|
||||||
|
<div className="flex items-center gap-1">
|
||||||
|
{(
|
||||||
|
[
|
||||||
|
{ k: "image2d" as TaskType, label: "图片 (2D)", count: assets.length, phase: "Phase 0", color: "var(--accent)" },
|
||||||
|
{ k: "model3d" as TaskType, label: "3D 模型", count: assets3D.length, phase: "Phase 2", color: "var(--gold)" },
|
||||||
|
{ k: "motion" as TaskType, label: "动作序列", count: assetsMotion.length, phase: "Phase 2", color: "var(--accent-secondary)" },
|
||||||
|
]
|
||||||
|
).map((t) => {
|
||||||
|
const active = modality === t.k;
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
key={t.k}
|
||||||
|
onClick={() => setModality(t.k)}
|
||||||
|
className="relative flex items-center gap-2 px-4 py-2.5 text-xs font-medium cursor-pointer transition-all"
|
||||||
|
style={{
|
||||||
|
color: active ? t.color : "var(--text-secondary)",
|
||||||
|
borderBottom: active ? `2px solid ${t.color}` : "2px solid transparent",
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{t.label}
|
||||||
|
<span
|
||||||
|
className="px-1.5 py-0.5 rounded-md text-[10px] font-mono"
|
||||||
|
style={{
|
||||||
|
backgroundColor: active ? t.color + "18" : "var(--bg-tertiary)",
|
||||||
|
color: active ? t.color : "var(--text-secondary)",
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{t.count}
|
||||||
|
</span>
|
||||||
|
{t.k !== "image2d" && <span className="phase-chip">{t.phase}</span>}
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
})}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
<div className="flex-1 flex overflow-hidden">
|
<div className="flex-1 flex overflow-hidden">
|
||||||
<main className="flex-1 flex flex-col min-w-0">
|
<main className="flex-1 flex flex-col min-w-0">
|
||||||
|
{modality === "model3d" ? (
|
||||||
|
<Assets3DGrid
|
||||||
|
items={assets3D}
|
||||||
|
onOpen={setDetail3D}
|
||||||
|
onDelete={deleteAsset3D}
|
||||||
|
/>
|
||||||
|
) : modality === "motion" ? (
|
||||||
|
<AssetsMotionGrid
|
||||||
|
items={assetsMotion}
|
||||||
|
onOpen={setDetailMotion}
|
||||||
|
onDelete={deleteAssetMotion}
|
||||||
|
/>
|
||||||
|
) : (
|
||||||
|
<>
|
||||||
{/* 工具栏 */}
|
{/* 工具栏 */}
|
||||||
<div className="flex-shrink-0 border-b border-[var(--border)] surface-1
|
<div className="flex-shrink-0 border-b border-[var(--border)] surface-1
|
||||||
backdrop-blur-xl px-4 md:px-5 py-3
|
backdrop-blur-xl px-4 md:px-5 py-3
|
||||||
@@ -629,8 +686,15 @@ export default function GalleryPage() {
|
|||||||
</div>
|
</div>
|
||||||
)}
|
)}
|
||||||
</div>
|
</div>
|
||||||
|
</>
|
||||||
|
)}
|
||||||
</main>
|
</main>
|
||||||
|
|
||||||
|
{/* 3D 详情面板 */}
|
||||||
|
{detail3D && <Model3DPanel asset={detail3D} onClose={() => setDetail3D(null)} />}
|
||||||
|
{/* 动作详情面板 */}
|
||||||
|
{detailMotion && <MotionPanel asset={detailMotion} onClose={() => setDetailMotion(null)} />}
|
||||||
|
|
||||||
{/* 详情 Modal */}
|
{/* 详情 Modal */}
|
||||||
{detailAsset && (
|
{detailAsset && (
|
||||||
<GalleryDetailModal
|
<GalleryDetailModal
|
||||||
@@ -799,3 +863,222 @@ function GalleryDetailModal({
|
|||||||
</div>
|
</div>
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/* ============ 3D 资产网格（占位简化版） ============ */
|
||||||
|
function Assets3DGrid({
|
||||||
|
items,
|
||||||
|
onOpen,
|
||||||
|
onDelete,
|
||||||
|
}: {
|
||||||
|
items: Asset3D[];
|
||||||
|
onOpen: (a: Asset3D) => void;
|
||||||
|
onDelete: (id: string) => void;
|
||||||
|
}) {
|
||||||
|
if (items.length === 0) {
|
||||||
|
return (
|
||||||
|
<div className="flex-1 flex items-center justify-center">
|
||||||
|
<motion.div className="text-center space-y-4" variants={staggerContainer} initial="hidden" animate="visible">
|
||||||
|
<motion.div
|
||||||
|
variants={staggerItem}
|
||||||
|
className="inline-flex items-center justify-center w-14 h-14 rounded-2xl
|
||||||
|
bg-[var(--gold)]/10 border border-[var(--gold)]/20"
|
||||||
|
>
|
||||||
|
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="var(--gold)" strokeWidth="1.5" opacity="0.7">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
<path d="M2 17l10 5 10-5" />
|
||||||
|
<path d="M2 12l10 5 10-5" />
|
||||||
|
</svg>
|
||||||
|
</motion.div>
|
||||||
|
<motion.p variants={staggerItem} className="typo-display text-lg">
|
||||||
|
还没有 3D 模型
|
||||||
|
</motion.p>
|
||||||
|
<motion.p variants={staggerItem} className="typo-caption">
|
||||||
|
在工作台切到「3D 模型」任务类型生成后，产物会出现在这里
|
||||||
|
</motion.p>
|
||||||
|
</motion.div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
return (
|
||||||
|
<div className="flex-1 overflow-y-auto p-4 md:p-5">
|
||||||
|
<div className="grid grid-cols-2 sm:grid-cols-3 lg:grid-cols-4 xl:grid-cols-5 gap-3 md:gap-4">
|
||||||
|
{items.map((a) => (
|
||||||
|
<div
|
||||||
|
key={a.id}
|
||||||
|
onClick={() => onOpen(a)}
|
||||||
|
className="group relative rounded-xl overflow-hidden neon-border cursor-pointer
|
||||||
|
bg-[var(--bg-card)] backdrop-blur-sm transition-all"
|
||||||
|
>
|
||||||
|
<div className="relative aspect-square bg-[var(--bg-primary)]">
|
||||||
|
{a.thumbnail || a.views[0]?.url ? (
|
||||||
|
<img src={a.thumbnail || a.views[0].url} alt={a.prompt ?? ""} className="w-full h-full object-cover
|
||||||
|
transition-transform duration-300 group-hover:scale-[1.03]" />
|
||||||
|
) : (
|
||||||
|
<div className="absolute inset-0 flex items-center justify-center">
|
||||||
|
<svg width="32" height="32" viewBox="0 0 24 24" fill="none" stroke="var(--gold)" strokeWidth="1.2" opacity="0.6">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
<path d="M2 17l10 5 10-5" />
|
||||||
|
<path d="M2 12l10 5 10-5" />
|
||||||
|
</svg>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
{/* 3D 徽章 */}
|
||||||
|
<div className="absolute top-2 left-2 flex items-center gap-1 px-1.5 py-0.5 rounded-md
|
||||||
|
bg-black/55 backdrop-blur-sm border border-[var(--gold)]/40">
|
||||||
|
<svg width="9" height="9" viewBox="0 0 24 24" fill="none" stroke="var(--gold)" strokeWidth="2.5">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
</svg>
|
||||||
|
<span className="text-[9px] font-bold tracking-wider" style={{ color: "var(--gold)" }}>3D</span>
|
||||||
|
</div>
|
||||||
|
{/* 视图数徽章 */}
|
||||||
|
<div className="absolute top-2 right-2 px-1.5 py-0.5 rounded-md
|
||||||
|
bg-black/55 backdrop-blur-sm text-[9px] text-white/85 font-mono">
|
||||||
|
{a.views.length} 视角
|
||||||
|
</div>
|
||||||
|
{/* 删除按钮 */}
|
||||||
|
<button
|
||||||
|
onClick={(e) => {
|
||||||
|
e.stopPropagation();
|
||||||
|
onDelete(a.id);
|
||||||
|
}}
|
||||||
|
className="absolute bottom-2 right-2 w-7 h-7 rounded-lg bg-black/50 backdrop-blur-sm
|
||||||
|
text-white/70 hover:text-[var(--hot)] flex items-center justify-center
|
||||||
|
opacity-100 md:opacity-0 md:group-hover:opacity-100 transition-all cursor-pointer"
|
||||||
|
title="删除"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polyline points="3 6 5 6 21 6" />
|
||||||
|
<path d="M19 6v14a2 2 0 01-2 2H7a2 2 0 01-2-2V6m3 0V4a2 2 0 012-2h4a2 2 0 012 2v2" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
<div className="p-2.5 bg-[var(--bg-secondary)]/80 backdrop-blur-sm">
|
||||||
|
<div className="text-[11px] text-[var(--text-primary)] truncate font-medium">
|
||||||
|
{a.prompt ?? "未命名模型"}
|
||||||
|
</div>
|
||||||
|
<div className="flex items-center justify-between mt-1">
|
||||||
|
<span className="text-[9px] text-[var(--text-secondary)] uppercase tracking-wider">
|
||||||
|
{a.pipeline}
|
||||||
|
</span>
|
||||||
|
<span className="text-[9px] text-[var(--text-secondary)]">
|
||||||
|
{new Date(a.createdAt).toLocaleDateString("zh-CN")}
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
/* ============ 动作序列网格（占位简化版） ============ */
|
||||||
|
function AssetsMotionGrid({
|
||||||
|
items,
|
||||||
|
onOpen,
|
||||||
|
onDelete,
|
||||||
|
}: {
|
||||||
|
items: AssetMotion[];
|
||||||
|
onOpen: (a: AssetMotion) => void;
|
||||||
|
onDelete: (id: string) => void;
|
||||||
|
}) {
|
||||||
|
if (items.length === 0) {
|
||||||
|
return (
|
||||||
|
<div className="flex-1 flex items-center justify-center">
|
||||||
|
<motion.div className="text-center space-y-4" variants={staggerContainer} initial="hidden" animate="visible">
|
||||||
|
<motion.div
|
||||||
|
variants={staggerItem}
|
||||||
|
className="inline-flex items-center justify-center w-14 h-14 rounded-2xl
|
||||||
|
bg-[var(--accent-secondary)]/10 border border-[var(--accent-secondary)]/20"
|
||||||
|
>
|
||||||
|
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="var(--accent-secondary)" strokeWidth="1.5" opacity="0.7">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
</motion.div>
|
||||||
|
<motion.p variants={staggerItem} className="typo-display text-lg">
|
||||||
|
还没有动作序列
|
||||||
|
</motion.p>
|
||||||
|
<motion.p variants={staggerItem} className="typo-caption">
|
||||||
|
在工作台切到「动作」任务类型生成后，产物会出现在这里
|
||||||
|
</motion.p>
|
||||||
|
</motion.div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
return (
|
||||||
|
<div className="flex-1 overflow-y-auto p-4 md:p-5">
|
||||||
|
<div className="grid grid-cols-2 sm:grid-cols-3 lg:grid-cols-4 xl:grid-cols-5 gap-3 md:gap-4">
|
||||||
|
{items.map((a) => (
|
||||||
|
<div
|
||||||
|
key={a.id}
|
||||||
|
onClick={() => onOpen(a)}
|
||||||
|
className="group relative rounded-xl overflow-hidden neon-border cursor-pointer
|
||||||
|
bg-[var(--bg-card)] backdrop-blur-sm transition-all"
|
||||||
|
>
|
||||||
|
<div className="relative aspect-square bg-[var(--bg-primary)]">
|
||||||
|
{a.videoUrl ? (
|
||||||
|
<video src={a.videoUrl} className="w-full h-full object-cover" muted loop playsInline
|
||||||
|
onMouseEnter={(e) => (e.currentTarget as HTMLVideoElement).play()}
|
||||||
|
onMouseLeave={(e) => {
|
||||||
|
const v = e.currentTarget as HTMLVideoElement;
|
||||||
|
v.pause();
|
||||||
|
v.currentTime = 0;
|
||||||
|
}} />
|
||||||
|
) : a.frames[0] ? (
|
||||||
|
<img src={a.frames[0]} alt={a.prompt ?? ""} className="w-full h-full object-cover" />
|
||||||
|
) : (
|
||||||
|
<div className="absolute inset-0 flex items-center justify-center">
|
||||||
|
<svg width="32" height="32" viewBox="0 0 24 24" fill="none" stroke="var(--accent-secondary)" strokeWidth="1.2" opacity="0.6">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
{/* 动作徽章 */}
|
||||||
|
<div className="absolute top-2 left-2 flex items-center gap-1 px-1.5 py-0.5 rounded-md
|
||||||
|
bg-black/55 backdrop-blur-sm border border-[var(--accent-secondary)]/40">
|
||||||
|
<svg width="9" height="9" viewBox="0 0 24 24" fill="currentColor" style={{ color: "var(--accent-secondary)" }}>
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
<span className="text-[9px] font-bold tracking-wider" style={{ color: "var(--accent-secondary)" }}>MOTION</span>
|
||||||
|
</div>
|
||||||
|
{/* 帧/FPS 徽章 */}
|
||||||
|
<div className="absolute top-2 right-2 px-1.5 py-0.5 rounded-md
|
||||||
|
bg-black/55 backdrop-blur-sm text-[9px] text-white/85 font-mono">
|
||||||
|
{a.frameCount}f · {a.fps}fps
|
||||||
|
</div>
|
||||||
|
{/* 删除按钮 */}
|
||||||
|
<button
|
||||||
|
onClick={(e) => {
|
||||||
|
e.stopPropagation();
|
||||||
|
onDelete(a.id);
|
||||||
|
}}
|
||||||
|
className="absolute bottom-2 right-2 w-7 h-7 rounded-lg bg-black/50 backdrop-blur-sm
|
||||||
|
text-white/70 hover:text-[var(--hot)] flex items-center justify-center
|
||||||
|
opacity-100 md:opacity-0 md:group-hover:opacity-100 transition-all cursor-pointer"
|
||||||
|
title="删除"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polyline points="3 6 5 6 21 6" />
|
||||||
|
<path d="M19 6v14a2 2 0 01-2 2H7a2 2 0 01-2-2V6m3 0V4a2 2 0 012-2h4a2 2 0 012 2v2" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
<div className="p-2.5 bg-[var(--bg-secondary)]/80 backdrop-blur-sm">
|
||||||
|
<div className="text-[11px] text-[var(--text-primary)] truncate font-medium">
|
||||||
|
{a.prompt || "未命名动作"}
|
||||||
|
</div>
|
||||||
|
<div className="flex items-center justify-between mt-1">
|
||||||
|
<span className="text-[9px] text-[var(--text-secondary)]">
|
||||||
|
{(a.frameCount / a.fps).toFixed(1)}s · {a.loop ? "循环" : "一次"}
|
||||||
|
</span>
|
||||||
|
<span className="text-[9px] text-[var(--text-secondary)]">
|
||||||
|
{new Date(a.createdAt).toLocaleDateString("zh-CN")}
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|||||||
@@ -1,7 +1,9 @@
|
|||||||
import type { Metadata } from "next";
|
import type { Metadata } from "next";
|
||||||
|
import Script from "next/script";
|
||||||
import { AuthProvider } from "@/lib/auth-context";
|
import { AuthProvider } from "@/lib/auth-context";
|
||||||
import { AuthGuard } from "@/lib/auth-guard";
|
import { AuthGuard } from "@/lib/auth-guard";
|
||||||
import { AppProvider } from "@/lib/app-context";
|
import { AppProvider } from "@/lib/app-context";
|
||||||
|
import { CommandPalette } from "@/components/docs/command-palette";
|
||||||
import "./globals.css";
|
import "./globals.css";
|
||||||
|
|
||||||
export const metadata: Metadata = {
|
export const metadata: Metadata = {
|
||||||
@@ -26,9 +28,18 @@ export default function RootLayout({
|
|||||||
<body className="antialiased">
|
<body className="antialiased">
|
||||||
<AuthProvider>
|
<AuthProvider>
|
||||||
<AuthGuard>
|
<AuthGuard>
|
||||||
<AppProvider>{children}</AppProvider>
|
<AppProvider>
|
||||||
|
{children}
|
||||||
|
<CommandPalette />
|
||||||
|
</AppProvider>
|
||||||
</AuthGuard>
|
</AuthGuard>
|
||||||
</AuthProvider>
|
</AuthProvider>
|
||||||
|
{/* <model-viewer> 自定义元素，供 3D 结果面板使用（占位） */}
|
||||||
|
<Script
|
||||||
|
type="module"
|
||||||
|
src="https://unpkg.com/@google/model-viewer/dist/model-viewer.min.js"
|
||||||
|
strategy="lazyOnload"
|
||||||
|
/>
|
||||||
</body>
|
</body>
|
||||||
</html>
|
</html>
|
||||||
);
|
);
|
||||||
|
|||||||
@@ -5,6 +5,9 @@ import { motion, AnimatePresence } from "framer-motion";
|
|||||||
import { ChatMessages } from "@/components/chat/chat-messages";
|
import { ChatMessages } from "@/components/chat/chat-messages";
|
||||||
import { ChatInput, type ChatInputHandle } from "@/components/chat/chat-input";
|
import { ChatInput, type ChatInputHandle } from "@/components/chat/chat-input";
|
||||||
import { SessionQuickPicks } from "@/components/chat/session-quick-picks";
|
import { SessionQuickPicks } from "@/components/chat/session-quick-picks";
|
||||||
|
import { TaskTypeTabs } from "@/components/chat/task-type-tabs";
|
||||||
|
import { Params3D } from "@/components/workbench/params-3d";
|
||||||
|
import { ParamsMotionBar } from "@/components/workbench/params-motion";
|
||||||
import { AdvancedControls } from "@/components/workbench/advanced-controls";
|
import { AdvancedControls } from "@/components/workbench/advanced-controls";
|
||||||
import { CandidatePanel } from "@/components/workbench/candidate-panel";
|
import { CandidatePanel } from "@/components/workbench/candidate-panel";
|
||||||
import { Sidebar } from "@/components/sidebar/sidebar";
|
import { Sidebar } from "@/components/sidebar/sidebar";
|
||||||
@@ -27,6 +30,7 @@ export default function Home() {
|
|||||||
detailImage,
|
detailImage,
|
||||||
sidebarCollapsed,
|
sidebarCollapsed,
|
||||||
setSidebarCollapsed,
|
setSidebarCollapsed,
|
||||||
|
sessionTaskType,
|
||||||
} = useApp();
|
} = useApp();
|
||||||
|
|
||||||
const messages = activeSession?.messages ?? [];
|
const messages = activeSession?.messages ?? [];
|
||||||
@@ -464,8 +468,15 @@ export default function Home() {
|
|||||||
)}
|
)}
|
||||||
</AnimatePresence>
|
</AnimatePresence>
|
||||||
|
|
||||||
<div className="flex-shrink-0 border-t border-[var(--border)] bg-[var(--bg-secondary)]/60 backdrop-blur-md
|
<div className="flex-shrink-0 border-t border-[var(--border)] bg-[var(--bg-secondary)]/60 backdrop-blur-md">
|
||||||
flex items-center">
|
{/* 任务类型切换（2D / 3D / 动作） */}
|
||||||
|
<TaskTypeTabs />
|
||||||
|
|
||||||
|
{/* 3D / 动作参数条（按任务类型显示） */}
|
||||||
|
{sessionTaskType === "model3d" && <Params3D />}
|
||||||
|
{sessionTaskType === "motion" && <ParamsMotionBar />}
|
||||||
|
|
||||||
|
<div className="flex items-center">
|
||||||
<div className="flex-1 min-w-0">
|
<div className="flex-1 min-w-0">
|
||||||
<SessionQuickPicks />
|
<SessionQuickPicks />
|
||||||
</div>
|
</div>
|
||||||
@@ -490,6 +501,7 @@ export default function Home() {
|
|||||||
</button>
|
</button>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
<ChatInput
|
<ChatInput
|
||||||
ref={chatInputRef}
|
ref={chatInputRef}
|
||||||
|
|||||||
@@ -2,14 +2,50 @@
|
|||||||
|
|
||||||
import { useState } from "react";
|
import { useState } from "react";
|
||||||
import { useApp } from "@/lib/app-context";
|
import { useApp } from "@/lib/app-context";
|
||||||
import type { TaskIR } from "@/lib/types";
|
import type { TaskIR, TaskType } from "@/lib/types";
|
||||||
|
|
||||||
interface TaskCardProps {
|
interface TaskCardProps {
|
||||||
ir: TaskIR;
|
ir: TaskIR;
|
||||||
|
/** 任务类型变体：2D / 3D / 动作。默认 image2d（向后兼容旧数据） */
|
||||||
|
variant?: TaskType;
|
||||||
onConfirm?: (ir: TaskIR) => void;
|
onConfirm?: (ir: TaskIR) => void;
|
||||||
onCancel?: () => void;
|
onCancel?: () => void;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
const VARIANT_META: Record<TaskType, { label: string; color: string; icon: React.ReactNode }> = {
|
||||||
|
image2d: {
|
||||||
|
label: "2D 图片生成",
|
||||||
|
color: "var(--accent)",
|
||||||
|
icon: (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<circle cx="8.5" cy="8.5" r="1.5" />
|
||||||
|
<polyline points="21 15 16 10 5 21" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
|
model3d: {
|
||||||
|
label: "3D 模型生成",
|
||||||
|
color: "var(--gold)",
|
||||||
|
icon: (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
<path d="M2 17l10 5 10-5" />
|
||||||
|
<path d="M2 12l10 5 10-5" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
|
motion: {
|
||||||
|
label: "动作序列生成",
|
||||||
|
color: "var(--accent-secondary)",
|
||||||
|
icon: (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
|
};
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* 任务说明卡（Phase 1 占位组件）
|
* 任务说明卡（Phase 1 占位组件）
|
||||||
*
|
*
|
||||||
@@ -17,23 +53,28 @@ interface TaskCardProps {
|
|||||||
* 用于在对话中展示 Agent 解析出的任务意图，供用户确认、微调或取消。
|
* 用于在对话中展示 Agent 解析出的任务意图，供用户确认、微调或取消。
|
||||||
* 数据结构见 types.ts 中的 TaskIR。
|
* 数据结构见 types.ts 中的 TaskIR。
|
||||||
*/
|
*/
|
||||||
export function TaskCard({ ir, onConfirm, onCancel }: TaskCardProps) {
|
export function TaskCard({ ir, variant = "image2d", onConfirm, onCancel }: TaskCardProps) {
|
||||||
const { stylePacks, characters } = useApp();
|
const { stylePacks, characters } = useApp();
|
||||||
const [candidateCount, setCandidateCount] = useState(ir.candidateCount);
|
const [candidateCount, setCandidateCount] = useState(ir.candidateCount);
|
||||||
|
|
||||||
const styleName = stylePacks.find((s) => s.id === ir.styleId)?.name;
|
const styleName = stylePacks.find((s) => s.id === ir.styleId)?.name;
|
||||||
const charName = characters.find((c) => c.id === ir.characterId)?.name;
|
const charName = characters.find((c) => c.id === ir.characterId)?.name;
|
||||||
|
const meta = VARIANT_META[variant];
|
||||||
|
|
||||||
return (
|
return (
|
||||||
<div className="rounded-xl border border-[var(--accent)]/20 bg-[var(--accent)]/5
|
<div
|
||||||
px-4 py-3 max-w-xl backdrop-blur-sm">
|
className="rounded-xl border px-4 py-3 max-w-xl backdrop-blur-sm"
|
||||||
|
style={{
|
||||||
|
borderColor: meta.color + "30",
|
||||||
|
backgroundColor: meta.color + "0A",
|
||||||
|
}}
|
||||||
|
>
|
||||||
<div className="flex items-center gap-2 mb-2">
|
<div className="flex items-center gap-2 mb-2">
|
||||||
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="var(--accent)" strokeWidth="2">
|
<span style={{ color: meta.color }}>{meta.icon}</span>
|
||||||
<path d="M9 11l3 3L22 4" />
|
<span className="typo-strong text-xs" style={{ color: meta.color }}>
|
||||||
<path d="M21 12v7a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h11" />
|
任务说明卡 · {meta.label}
|
||||||
</svg>
|
</span>
|
||||||
<span className="typo-strong text-xs text-[var(--accent)]">任务说明卡</span>
|
<span className="phase-chip">{variant === "image2d" ? "Phase 1" : "Phase 2"}</span>
|
||||||
<span className="phase-chip">Phase 1</span>
|
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div className="grid grid-cols-1 sm:grid-cols-2 gap-x-4 gap-y-1.5 text-xs">
|
<div className="grid grid-cols-1 sm:grid-cols-2 gap-x-4 gap-y-1.5 text-xs">
|
||||||
@@ -61,6 +102,42 @@ export function TaskCard({ ir, onConfirm, onCancel }: TaskCardProps) {
|
|||||||
<span className="typo-micro" style={{ textTransform: "none" }}>输出规格</span>
|
<span className="typo-micro" style={{ textTransform: "none" }}>输出规格</span>
|
||||||
<div className="text-[var(--text-primary)]">{ir.outputSpec}</div>
|
<div className="text-[var(--text-primary)]">{ir.outputSpec}</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
|
{/* 3D 变体专有字段 */}
|
||||||
|
{variant === "model3d" && (
|
||||||
|
<>
|
||||||
|
<div>
|
||||||
|
<span className="typo-micro" style={{ textTransform: "none" }}>管道</span>
|
||||||
|
<div className="text-[var(--text-primary)]">Trellis / Hunyuan3D</div>
|
||||||
|
</div>
|
||||||
|
<div>
|
||||||
|
<span className="typo-micro" style={{ textTransform: "none" }}>视图数</span>
|
||||||
|
<div className="text-[var(--text-primary)]">6 视角（等距）</div>
|
||||||
|
</div>
|
||||||
|
<div className="sm:col-span-2">
|
||||||
|
<span className="typo-micro" style={{ textTransform: "none" }}>产物</span>
|
||||||
|
<div className="text-[var(--text-primary)]">多视图 PNG · 法线图 · 风格化图 · .glb 模型</div>
|
||||||
|
</div>
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{/* 动作变体专有字段 */}
|
||||||
|
{variant === "motion" && (
|
||||||
|
<>
|
||||||
|
<div>
|
||||||
|
<span className="typo-micro" style={{ textTransform: "none" }}>帧数 · 帧率</span>
|
||||||
|
<div className="text-[var(--text-primary)]">16 帧 · 12 fps（≈ 1.3s）</div>
|
||||||
|
</div>
|
||||||
|
<div>
|
||||||
|
<span className="typo-micro" style={{ textTransform: "none" }}>循环</span>
|
||||||
|
<div className="text-[var(--text-primary)]">是</div>
|
||||||
|
</div>
|
||||||
|
<div className="sm:col-span-2">
|
||||||
|
<span className="typo-micro" style={{ textTransform: "none" }}>产物</span>
|
||||||
|
<div className="text-[var(--text-primary)]">MP4 视频 · 帧序列（可选 GIF）</div>
|
||||||
|
</div>
|
||||||
|
</>
|
||||||
|
)}
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div className="mt-3 flex items-center gap-3 flex-wrap">
|
<div className="mt-3 flex items-center gap-3 flex-wrap">
|
||||||
@@ -90,10 +167,9 @@ export function TaskCard({ ir, onConfirm, onCancel }: TaskCardProps) {
|
|||||||
)}
|
)}
|
||||||
<button
|
<button
|
||||||
onClick={() => onConfirm?.({ ...ir, candidateCount })}
|
onClick={() => onConfirm?.({ ...ir, candidateCount })}
|
||||||
className="px-2.5 py-1 text-xs rounded-md font-medium
|
className="px-2.5 py-1 text-xs rounded-md font-medium text-[var(--bg-primary)]
|
||||||
bg-[var(--accent)] text-[var(--bg-primary)]
|
hover:opacity-90 cursor-pointer transition-all"
|
||||||
hover:bg-[var(--accent-hover)]
|
style={{ backgroundColor: meta.color }}
|
||||||
cursor-pointer transition-all"
|
|
||||||
>
|
>
|
||||||
确认并生成
|
确认并生成
|
||||||
</button>
|
</button>
|
||||||
@@ -101,7 +177,9 @@ export function TaskCard({ ir, onConfirm, onCancel }: TaskCardProps) {
|
|||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div className="text-[10px] text-[var(--text-secondary)] mt-2">
|
<div className="text-[10px] text-[var(--text-secondary)] mt-2">
|
||||||
确认后 Agent 将按此参数组合生成候选（占位交互，真实链路待 Phase 1）。
|
{variant === "image2d" && "确认后 Agent 将按此参数组合生成候选（占位交互，真实链路待 Phase 1）。"}
|
||||||
|
{variant === "model3d" && "3D 管线：单图 → 多视图 → 法线 → 风格化 → GLB（占位，真实链路待 Phase 2）。"}
|
||||||
|
{variant === "motion" && "动作管线：立绘 / 角色 LoRA → 运动编码 → 视频（占位，真实链路待 Phase 2）。"}
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
);
|
);
|
||||||
|
|||||||
85
art-agent/frontend/src/components/chat/task-type-tabs.tsx
Normal file
85
art-agent/frontend/src/components/chat/task-type-tabs.tsx
Normal file
@@ -0,0 +1,85 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import type { TaskType } from "@/lib/types";
|
||||||
|
|
||||||
|
const TASK_TYPES: { id: TaskType; label: string; phase: string; icon: React.ReactNode }[] = [
|
||||||
|
{
|
||||||
|
id: "image2d",
|
||||||
|
label: "2D 图片",
|
||||||
|
phase: "P0",
|
||||||
|
icon: (
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<circle cx="8.5" cy="8.5" r="1.5" />
|
||||||
|
<polyline points="21 15 16 10 5 21" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "model3d",
|
||||||
|
label: "3D 模型",
|
||||||
|
phase: "P2",
|
||||||
|
icon: (
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
<path d="M2 17l10 5 10-5" />
|
||||||
|
<path d="M2 12l10 5 10-5" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "motion",
|
||||||
|
label: "动作序列",
|
||||||
|
phase: "P2",
|
||||||
|
icon: (
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
|
];
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 工作台任务类型切换（2D / 3D / 动作）。
|
||||||
|
*
|
||||||
|
* 切换后会影响：
|
||||||
|
* - 下方"任务说明卡"的变体
|
||||||
|
* - 参数条组件（Params3D / ParamsMotion）是否可见
|
||||||
|
* - 发送后生成物的归类（2D image / 3D asset / motion asset）
|
||||||
|
*/
|
||||||
|
export function TaskTypeTabs() {
|
||||||
|
const { sessionTaskType, setSessionTaskType } = useApp();
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="flex items-center gap-1 px-3 md:px-5 pt-2 pb-0 flex-wrap">
|
||||||
|
<span className="typo-micro text-[10px] mr-1" style={{ textTransform: "none" }}>
|
||||||
|
任务
|
||||||
|
</span>
|
||||||
|
<div className="flex items-center gap-0.5 p-0.5 rounded-lg bg-[var(--bg-tertiary)] border border-[var(--border)]">
|
||||||
|
{TASK_TYPES.map((t) => {
|
||||||
|
const active = sessionTaskType === t.id;
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
key={t.id}
|
||||||
|
onClick={() => setSessionTaskType(t.id)}
|
||||||
|
className={`relative h-6 px-2 rounded-md text-[11px] flex items-center gap-1 cursor-pointer
|
||||||
|
transition-all whitespace-nowrap ${
|
||||||
|
active
|
||||||
|
? "bg-[var(--accent)]/12 text-[var(--accent)] shadow-[0_0_8px_rgba(46,139,122,0.1)]"
|
||||||
|
: "text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
title={`${t.label}（${t.phase}）`}
|
||||||
|
>
|
||||||
|
{t.icon}
|
||||||
|
<span className="font-medium">{t.label}</span>
|
||||||
|
{!active && t.phase !== "P0" && (
|
||||||
|
<span className="phase-chip ml-0.5">{t.phase}</span>
|
||||||
|
)}
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
})}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
262
art-agent/frontend/src/components/detail/model-3d-panel.tsx
Normal file
262
art-agent/frontend/src/components/detail/model-3d-panel.tsx
Normal file
@@ -0,0 +1,262 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { createElement, useState } from "react";
|
||||||
|
import { motion } from "framer-motion";
|
||||||
|
import { slideUp } from "@/components/ui/motion-presets";
|
||||||
|
import type { Asset3D } from "@/lib/types";
|
||||||
|
|
||||||
|
interface Model3DPanelProps {
|
||||||
|
asset: Asset3D;
|
||||||
|
onClose?: () => void;
|
||||||
|
}
|
||||||
|
|
||||||
|
type ViewChannel = "color" | "normal" | "stylized";
|
||||||
|
const VIEW_TABS: { key: ViewChannel; label: string }[] = [
|
||||||
|
{ key: "color", label: "原图" },
|
||||||
|
{ key: "normal", label: "法线" },
|
||||||
|
{ key: "stylized", label: "风格化" },
|
||||||
|
];
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 3D 结果面板（占位）：支持多视图切换、360 旋转、<model-viewer> 预览。
|
||||||
|
* 真实模型文件加载待 Phase 2 接入 Trellis/Hunyuan3D 管线。
|
||||||
|
*/
|
||||||
|
export function Model3DPanel({ asset, onClose }: Model3DPanelProps) {
|
||||||
|
const [mode, setMode] = useState<"views" | "rotate" | "mesh">("views");
|
||||||
|
const [viewTab, setViewTab] = useState<ViewChannel>("color");
|
||||||
|
const [activeViewIdx, setActiveViewIdx] = useState(0);
|
||||||
|
|
||||||
|
const activeView = asset.views[activeViewIdx];
|
||||||
|
const imgSrc =
|
||||||
|
viewTab === "color"
|
||||||
|
? activeView?.url
|
||||||
|
: viewTab === "normal"
|
||||||
|
? activeView?.normalUrl
|
||||||
|
: activeView?.restyledUrl;
|
||||||
|
|
||||||
|
return (
|
||||||
|
<motion.aside
|
||||||
|
variants={slideUp}
|
||||||
|
initial="hidden"
|
||||||
|
animate="visible"
|
||||||
|
className="fixed inset-0 z-50 md:relative md:inset-auto md:z-auto
|
||||||
|
md:w-[420px] flex-shrink-0 border-l border-[var(--border)]
|
||||||
|
bg-[var(--bg-secondary)]/90 backdrop-blur-xl
|
||||||
|
flex flex-col overflow-hidden"
|
||||||
|
>
|
||||||
|
{/* 头部 */}
|
||||||
|
<div className="flex items-center justify-between px-4 py-3 border-b border-[var(--border)]">
|
||||||
|
<div className="flex items-center gap-2">
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="var(--gold)" strokeWidth="2">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
<path d="M2 17l10 5 10-5" />
|
||||||
|
<path d="M2 12l10 5 10-5" />
|
||||||
|
</svg>
|
||||||
|
<span className="text-sm font-semibold text-[var(--text-primary)]">3D 模型详情</span>
|
||||||
|
<span className="phase-chip">Phase 2</span>
|
||||||
|
</div>
|
||||||
|
<button
|
||||||
|
onClick={onClose}
|
||||||
|
className="text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
cursor-pointer transition-colors p-1 rounded-lg hover:bg-[var(--accent)]/5"
|
||||||
|
>
|
||||||
|
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M18 6L6 18M6 6l12 12" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div className="flex-1 overflow-y-auto">
|
||||||
|
{/* 模式切换 */}
|
||||||
|
<div className="p-3 flex gap-1 border-b border-[var(--border)]">
|
||||||
|
{(
|
||||||
|
[
|
||||||
|
{ k: "views", l: "多视图" },
|
||||||
|
{ k: "rotate", l: "360°" },
|
||||||
|
{ k: "mesh", l: "模型" },
|
||||||
|
] as const
|
||||||
|
).map((m) => (
|
||||||
|
<button
|
||||||
|
key={m.k}
|
||||||
|
onClick={() => setMode(m.k)}
|
||||||
|
className={`flex-1 text-xs px-2 py-1.5 rounded-lg font-medium transition-all cursor-pointer ${
|
||||||
|
mode === m.k
|
||||||
|
? "bg-[var(--gold)]/15 text-[var(--gold)] border border-[var(--gold)]/40"
|
||||||
|
: "bg-[var(--bg-tertiary)] text-[var(--text-secondary)] border border-[var(--border)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{m.l}
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 预览区 */}
|
||||||
|
<div className="p-4">
|
||||||
|
<div className="relative rounded-xl overflow-hidden neon-border bg-[var(--bg-primary)] aspect-square">
|
||||||
|
{mode === "views" && imgSrc && (
|
||||||
|
<img src={imgSrc} alt="view" className="w-full h-full object-contain" />
|
||||||
|
)}
|
||||||
|
{mode === "views" && !imgSrc && (
|
||||||
|
<div className="absolute inset-0 flex items-center justify-center text-[var(--text-secondary)] text-xs">
|
||||||
|
暂无 {viewTab} 通道占位图
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{mode === "rotate" && (
|
||||||
|
<div className="absolute inset-0 flex flex-col items-center justify-center gap-3 text-[var(--text-secondary)] text-xs">
|
||||||
|
<motion.div
|
||||||
|
animate={{ rotateY: 360 }}
|
||||||
|
transition={{ duration: 8, ease: "linear", repeat: Infinity }}
|
||||||
|
style={{ transformStyle: "preserve-3d" as const, perspective: "400px" }}
|
||||||
|
className="w-20 h-20 flex items-center justify-center"
|
||||||
|
>
|
||||||
|
<svg width="80" height="80" viewBox="0 0 80 80" fill="none" stroke="var(--gold)" strokeWidth="1.5">
|
||||||
|
<polygon points="40,10 70,25 70,55 40,70 10,55 10,25" fill="color-mix(in srgb, var(--gold) 10%, transparent)" />
|
||||||
|
<line x1="40" y1="10" x2="40" y2="70" />
|
||||||
|
<line x1="10" y1="25" x2="70" y2="25" />
|
||||||
|
<line x1="10" y1="55" x2="70" y2="55" />
|
||||||
|
</svg>
|
||||||
|
</motion.div>
|
||||||
|
<span>360° 旋转预览（占位）</span>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{mode === "mesh" && (
|
||||||
|
<div className="absolute inset-0 flex items-center justify-center">
|
||||||
|
{asset.meshUrl ? (
|
||||||
|
createElement("model-viewer", {
|
||||||
|
src: asset.meshUrl,
|
||||||
|
"camera-controls": true,
|
||||||
|
"auto-rotate": true,
|
||||||
|
ar: true,
|
||||||
|
exposure: "1",
|
||||||
|
style: { width: "100%", height: "100%" },
|
||||||
|
})
|
||||||
|
) : (
|
||||||
|
<div className="text-[var(--text-secondary)] text-xs flex flex-col items-center gap-2">
|
||||||
|
<svg width="32" height="32" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="1.5">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
<path d="M2 17l10 5 10-5" />
|
||||||
|
<path d="M2 12l10 5 10-5" />
|
||||||
|
</svg>
|
||||||
|
<span>GLB 模型生成中...（占位）</span>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 多视图：通道 Tab */}
|
||||||
|
{mode === "views" && (
|
||||||
|
<div className="mt-3">
|
||||||
|
<div className="flex gap-1 mb-2">
|
||||||
|
{VIEW_TABS.map((t) => (
|
||||||
|
<button
|
||||||
|
key={t.key}
|
||||||
|
onClick={() => setViewTab(t.key)}
|
||||||
|
className={`text-[10px] px-2 py-0.5 rounded-md font-medium transition-all cursor-pointer ${
|
||||||
|
viewTab === t.key
|
||||||
|
? "bg-[var(--accent)]/15 text-[var(--accent)]"
|
||||||
|
: "text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{t.label}
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 视图缩略条 */}
|
||||||
|
<div className="flex gap-1.5 overflow-x-auto pb-1">
|
||||||
|
{asset.views.map((v, i) => {
|
||||||
|
const label = `方位 ${Math.round(v.azimuth)}° · 仰角 ${Math.round(v.elevation)}°`;
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
key={i}
|
||||||
|
onClick={() => setActiveViewIdx(i)}
|
||||||
|
className={`flex-shrink-0 w-14 h-14 rounded-lg overflow-hidden border-2 transition-all cursor-pointer ${
|
||||||
|
i === activeViewIdx ? "border-[var(--gold)]" : "border-transparent opacity-70 hover:opacity-100"
|
||||||
|
}`}
|
||||||
|
title={label}
|
||||||
|
>
|
||||||
|
<img src={v.url} alt={label} className="w-full h-full object-cover" />
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
})}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 操作按钮 */}
|
||||||
|
<div className="px-4 pb-3 flex flex-wrap gap-2">
|
||||||
|
<button
|
||||||
|
className="flex items-center gap-1.5 px-3.5 py-2 text-xs rounded-xl font-medium
|
||||||
|
bg-[var(--gold)] text-[var(--bg-primary)]
|
||||||
|
hover:opacity-90 transition-all cursor-pointer btn-hover-lift"
|
||||||
|
title="下载 GLB（占位）"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M21 15v4a2 2 0 01-2 2H5a2 2 0 01-2-2v-4M7 10l5 5 5-5M12 15V3" />
|
||||||
|
</svg>
|
||||||
|
下载 GLB
|
||||||
|
</button>
|
||||||
|
<button
|
||||||
|
className="flex items-center gap-1.5 px-3.5 py-2 text-xs rounded-xl font-medium
|
||||||
|
bg-[var(--bg-tertiary)] text-[var(--text-secondary)]
|
||||||
|
hover:text-[var(--text-primary)] border border-[var(--border)]
|
||||||
|
hover:border-[var(--gold)]/40 transition-all cursor-pointer btn-hover-lift"
|
||||||
|
title="重新生成（占位）"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M21 12a9 9 0 11-3-6.7L21 8M21 3v5h-5" />
|
||||||
|
</svg>
|
||||||
|
重跑
|
||||||
|
</button>
|
||||||
|
<button
|
||||||
|
className="flex items-center gap-1.5 px-3.5 py-2 text-xs rounded-xl font-medium
|
||||||
|
bg-[var(--bg-tertiary)] text-[var(--text-secondary)]
|
||||||
|
hover:text-[var(--text-primary)] border border-[var(--border)]
|
||||||
|
hover:border-[var(--accent)]/40 transition-all cursor-pointer btn-hover-lift"
|
||||||
|
title="基于此模型生成动作（占位）"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
驱动动作
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 元信息 */}
|
||||||
|
<div className="px-4 pb-4 space-y-3">
|
||||||
|
<div>
|
||||||
|
<span className="typo-caption font-medium block mb-1.5">管线</span>
|
||||||
|
<div className="text-xs text-[var(--text-secondary)]">
|
||||||
|
{asset.pipeline === "trellis"
|
||||||
|
? "Trellis（3D Gaussians → Mesh）"
|
||||||
|
: asset.pipeline === "hunyuan3d"
|
||||||
|
? "Hunyuan3D（腾讯开源）"
|
||||||
|
: "Zero123++（多视图合成）"}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
{asset.prompt && (
|
||||||
|
<div>
|
||||||
|
<span className="typo-caption font-medium block mb-1.5">Prompt</span>
|
||||||
|
<div className="p-3 rounded-xl bg-[var(--bg-primary)] border border-[var(--border)]
|
||||||
|
text-xs text-[var(--text-secondary)] leading-relaxed break-all">
|
||||||
|
{asset.prompt}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
<div>
|
||||||
|
<span className="typo-caption font-medium block mb-1.5">信息</span>
|
||||||
|
<div className="text-xs text-[var(--text-secondary)] space-y-1">
|
||||||
|
<div>视图数：{asset.views.length}</div>
|
||||||
|
<div>创建时间：{new Date(asset.createdAt).toLocaleString("zh-CN")}</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
</motion.aside>
|
||||||
|
);
|
||||||
|
}
|
||||||
259
art-agent/frontend/src/components/detail/motion-panel.tsx
Normal file
259
art-agent/frontend/src/components/detail/motion-panel.tsx
Normal file
@@ -0,0 +1,259 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useEffect, useRef, useState } from "react";
|
||||||
|
import { motion } from "framer-motion";
|
||||||
|
import { slideUp } from "@/components/ui/motion-presets";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import type { AssetMotion } from "@/lib/types";
|
||||||
|
|
||||||
|
interface MotionPanelProps {
|
||||||
|
asset: AssetMotion;
|
||||||
|
onClose?: () => void;
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 动作序列结果面板（占位）：
|
||||||
|
* - 视频/帧序列预览
|
||||||
|
* - 播放/暂停/帧擦写（scrubber）
|
||||||
|
* - 下载 MP4 / GIF / 帧序列占位按钮
|
||||||
|
*/
|
||||||
|
export function MotionPanel({ asset, onClose }: MotionPanelProps) {
|
||||||
|
const { characters } = useApp();
|
||||||
|
const videoRef = useRef<HTMLVideoElement>(null);
|
||||||
|
const [playing, setPlaying] = useState(false);
|
||||||
|
const [frameIdx, setFrameIdx] = useState(0);
|
||||||
|
const [mode, setMode] = useState<"video" | "frames">("video");
|
||||||
|
|
||||||
|
const character = characters.find((c) => c.id === asset.characterId);
|
||||||
|
|
||||||
|
// 帧序列自动播放
|
||||||
|
useEffect(() => {
|
||||||
|
if (mode !== "frames" || !playing || asset.frames.length === 0) return;
|
||||||
|
const iv = setInterval(() => {
|
||||||
|
setFrameIdx((i) => (i + 1) % asset.frames.length);
|
||||||
|
}, 1000 / asset.fps);
|
||||||
|
return () => clearInterval(iv);
|
||||||
|
}, [mode, playing, asset.frames.length, asset.fps]);
|
||||||
|
|
||||||
|
const togglePlay = () => {
|
||||||
|
if (mode === "video") {
|
||||||
|
if (!videoRef.current) return;
|
||||||
|
if (videoRef.current.paused) {
|
||||||
|
videoRef.current.play();
|
||||||
|
setPlaying(true);
|
||||||
|
} else {
|
||||||
|
videoRef.current.pause();
|
||||||
|
setPlaying(false);
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
setPlaying((p) => !p);
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
return (
|
||||||
|
<motion.aside
|
||||||
|
variants={slideUp}
|
||||||
|
initial="hidden"
|
||||||
|
animate="visible"
|
||||||
|
className="fixed inset-0 z-50 md:relative md:inset-auto md:z-auto
|
||||||
|
md:w-[420px] flex-shrink-0 border-l border-[var(--border)]
|
||||||
|
bg-[var(--bg-secondary)]/90 backdrop-blur-xl
|
||||||
|
flex flex-col overflow-hidden"
|
||||||
|
>
|
||||||
|
{/* 头部 */}
|
||||||
|
<div className="flex items-center justify-between px-4 py-3 border-b border-[var(--border)]">
|
||||||
|
<div className="flex items-center gap-2">
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="var(--accent-secondary)" strokeWidth="2">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
<span className="text-sm font-semibold text-[var(--text-primary)]">动作序列详情</span>
|
||||||
|
<span className="phase-chip">Phase 2</span>
|
||||||
|
</div>
|
||||||
|
<button
|
||||||
|
onClick={onClose}
|
||||||
|
className="text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
cursor-pointer transition-colors p-1 rounded-lg hover:bg-[var(--accent)]/5"
|
||||||
|
>
|
||||||
|
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M18 6L6 18M6 6l12 12" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div className="flex-1 overflow-y-auto">
|
||||||
|
{/* 模式切换 */}
|
||||||
|
<div className="p-3 flex gap-1 border-b border-[var(--border)]">
|
||||||
|
{(
|
||||||
|
[
|
||||||
|
{ k: "video", l: "视频" },
|
||||||
|
{ k: "frames", l: "帧序列" },
|
||||||
|
] as const
|
||||||
|
).map((m) => (
|
||||||
|
<button
|
||||||
|
key={m.k}
|
||||||
|
onClick={() => {
|
||||||
|
setMode(m.k);
|
||||||
|
setPlaying(false);
|
||||||
|
}}
|
||||||
|
className={`flex-1 text-xs px-2 py-1.5 rounded-lg font-medium transition-all cursor-pointer ${
|
||||||
|
mode === m.k
|
||||||
|
? "bg-[var(--accent-secondary)]/15 text-[var(--accent-secondary)] border border-[var(--accent-secondary)]/40"
|
||||||
|
: "bg-[var(--bg-tertiary)] text-[var(--text-secondary)] border border-[var(--border)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{m.l}
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 预览 */}
|
||||||
|
<div className="p-4">
|
||||||
|
<div className="relative rounded-xl overflow-hidden neon-border bg-[var(--bg-primary)] aspect-square">
|
||||||
|
{mode === "video" ? (
|
||||||
|
asset.videoUrl ? (
|
||||||
|
<video
|
||||||
|
ref={videoRef}
|
||||||
|
src={asset.videoUrl}
|
||||||
|
className="w-full h-full object-contain"
|
||||||
|
loop={asset.loop}
|
||||||
|
muted
|
||||||
|
playsInline
|
||||||
|
onPlay={() => setPlaying(true)}
|
||||||
|
onPause={() => setPlaying(false)}
|
||||||
|
/>
|
||||||
|
) : (
|
||||||
|
<div className="absolute inset-0 flex items-center justify-center text-[var(--text-secondary)] text-xs">
|
||||||
|
视频生成中...（占位）
|
||||||
|
</div>
|
||||||
|
)
|
||||||
|
) : asset.frames.length > 0 ? (
|
||||||
|
<img src={asset.frames[frameIdx]} alt={`frame ${frameIdx}`} className="w-full h-full object-contain" />
|
||||||
|
) : (
|
||||||
|
<div className="absolute inset-0 flex items-center justify-center text-[var(--text-secondary)] text-xs">
|
||||||
|
帧序列占位
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 播放控件 */}
|
||||||
|
<div className="mt-3 flex items-center gap-2">
|
||||||
|
<button
|
||||||
|
onClick={togglePlay}
|
||||||
|
className="flex items-center justify-center w-9 h-9 rounded-full
|
||||||
|
bg-[var(--accent-secondary)] text-[var(--bg-primary)]
|
||||||
|
hover:opacity-90 cursor-pointer transition-all"
|
||||||
|
>
|
||||||
|
{playing ? (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor">
|
||||||
|
<rect x="6" y="4" width="4" height="16" />
|
||||||
|
<rect x="14" y="4" width="4" height="16" />
|
||||||
|
</svg>
|
||||||
|
) : (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
)}
|
||||||
|
</button>
|
||||||
|
|
||||||
|
{mode === "frames" && asset.frames.length > 0 && (
|
||||||
|
<>
|
||||||
|
<input
|
||||||
|
type="range"
|
||||||
|
min={0}
|
||||||
|
max={asset.frames.length - 1}
|
||||||
|
value={frameIdx}
|
||||||
|
onChange={(e) => setFrameIdx(Number(e.target.value))}
|
||||||
|
className="flex-1 accent-[var(--accent-secondary)]"
|
||||||
|
/>
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)] font-mono min-w-[40px] text-right">
|
||||||
|
{frameIdx + 1}/{asset.frames.length}
|
||||||
|
</span>
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{mode === "video" && (
|
||||||
|
<div className="flex-1 text-[10px] text-[var(--text-secondary)]">
|
||||||
|
{asset.frameCount} 帧 · {asset.fps} fps · {(asset.frameCount / asset.fps).toFixed(2)}s
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 操作 */}
|
||||||
|
<div className="px-4 pb-3 flex flex-wrap gap-2">
|
||||||
|
<button
|
||||||
|
className="flex items-center gap-1.5 px-3.5 py-2 text-xs rounded-xl font-medium
|
||||||
|
bg-[var(--accent-secondary)] text-[var(--bg-primary)]
|
||||||
|
hover:opacity-90 transition-all cursor-pointer btn-hover-lift"
|
||||||
|
title="下载 MP4（占位）"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M21 15v4a2 2 0 01-2 2H5a2 2 0 01-2-2v-4M7 10l5 5 5-5M12 15V3" />
|
||||||
|
</svg>
|
||||||
|
MP4
|
||||||
|
</button>
|
||||||
|
<button
|
||||||
|
className="flex items-center gap-1.5 px-3.5 py-2 text-xs rounded-xl font-medium
|
||||||
|
bg-[var(--bg-tertiary)] text-[var(--text-secondary)]
|
||||||
|
hover:text-[var(--text-primary)] border border-[var(--border)]
|
||||||
|
hover:border-[var(--accent-secondary)]/40 transition-all cursor-pointer btn-hover-lift"
|
||||||
|
title="下载 GIF（占位）"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M21 15v4a2 2 0 01-2 2H5a2 2 0 01-2-2v-4M7 10l5 5 5-5M12 15V3" />
|
||||||
|
</svg>
|
||||||
|
GIF
|
||||||
|
</button>
|
||||||
|
<button
|
||||||
|
className="flex items-center gap-1.5 px-3.5 py-2 text-xs rounded-xl font-medium
|
||||||
|
bg-[var(--bg-tertiary)] text-[var(--text-secondary)]
|
||||||
|
hover:text-[var(--text-primary)] border border-[var(--border)]
|
||||||
|
hover:border-[var(--accent-secondary)]/40 transition-all cursor-pointer btn-hover-lift"
|
||||||
|
title="下载帧序列 zip（占位）"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="7" height="7" />
|
||||||
|
<rect x="14" y="3" width="7" height="7" />
|
||||||
|
<rect x="3" y="14" width="7" height="7" />
|
||||||
|
<rect x="14" y="14" width="7" height="7" />
|
||||||
|
</svg>
|
||||||
|
帧序列
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 元信息 */}
|
||||||
|
<div className="px-4 pb-4 space-y-3">
|
||||||
|
{asset.prompt && (
|
||||||
|
<div>
|
||||||
|
<span className="typo-caption font-medium block mb-1.5">动作描述</span>
|
||||||
|
<div className="p-3 rounded-xl bg-[var(--bg-primary)] border border-[var(--border)]
|
||||||
|
text-xs text-[var(--text-secondary)] leading-relaxed break-all">
|
||||||
|
{asset.prompt}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
{character && (
|
||||||
|
<div>
|
||||||
|
<span className="typo-caption font-medium block mb-1.5">角色绑定</span>
|
||||||
|
<div className="flex items-center gap-2">
|
||||||
|
<div className="w-7 h-7 rounded-full flex items-center justify-center text-xs font-bold"
|
||||||
|
style={{ backgroundColor: "var(--accent)" + "22", color: "var(--accent)" }}>
|
||||||
|
{character.name.slice(0, 1)}
|
||||||
|
</div>
|
||||||
|
<span className="text-xs text-[var(--text-primary)]">{character.name}</span>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
<div>
|
||||||
|
<span className="typo-caption font-medium block mb-1.5">信息</span>
|
||||||
|
<div className="text-xs text-[var(--text-secondary)] space-y-1">
|
||||||
|
<div>帧数 / 帧率：{asset.frameCount} 帧 · {asset.fps} fps</div>
|
||||||
|
<div>循环：{asset.loop ? "是" : "否"}</div>
|
||||||
|
<div>创建时间：{new Date(asset.createdAt).toLocaleString("zh-CN")}</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</motion.aside>
|
||||||
|
);
|
||||||
|
}
|
||||||
206
art-agent/frontend/src/components/docs/asset-picker.tsx
Normal file
206
art-agent/frontend/src/components/docs/asset-picker.tsx
Normal file
@@ -0,0 +1,206 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useState, useMemo, useEffect, useRef } from "react";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import { getImageUrl } from "@/lib/api";
|
||||||
|
|
||||||
|
interface AssetPickerProps {
|
||||||
|
onInsert: (assetRef: string) => void;
|
||||||
|
onClose: () => void;
|
||||||
|
}
|
||||||
|
|
||||||
|
type Kind = "all" | "image" | "character" | "style";
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 资产引用选择器浮层（按 @ 键或工具条按钮唤起）。
|
||||||
|
*
|
||||||
|
* 产物：将选中的资产作为 [[asset:<id>]] 插入到文档。
|
||||||
|
*/
|
||||||
|
export function AssetPicker({ onInsert, onClose }: AssetPickerProps) {
|
||||||
|
const { assets, characters, stylePacks } = useApp();
|
||||||
|
const [kind, setKind] = useState<Kind>("all");
|
||||||
|
const [query, setQuery] = useState("");
|
||||||
|
const inputRef = useRef<HTMLInputElement>(null);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
inputRef.current?.focus();
|
||||||
|
}, []);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
const handler = (e: KeyboardEvent) => {
|
||||||
|
if (e.key === "Escape") {
|
||||||
|
e.preventDefault();
|
||||||
|
onClose();
|
||||||
|
}
|
||||||
|
};
|
||||||
|
window.addEventListener("keydown", handler);
|
||||||
|
return () => window.removeEventListener("keydown", handler);
|
||||||
|
}, [onClose]);
|
||||||
|
|
||||||
|
const results = useMemo(() => {
|
||||||
|
const q = query.toLowerCase();
|
||||||
|
const out: Array<{
|
||||||
|
id: string;
|
||||||
|
kind: "image" | "character" | "style";
|
||||||
|
label: string;
|
||||||
|
sublabel?: string;
|
||||||
|
thumb?: string;
|
||||||
|
}> = [];
|
||||||
|
if (kind === "all" || kind === "image") {
|
||||||
|
for (const a of assets) {
|
||||||
|
if (q && !a.prompt.toLowerCase().includes(q) && !a.id.includes(q)) continue;
|
||||||
|
out.push({
|
||||||
|
id: a.id,
|
||||||
|
kind: "image",
|
||||||
|
label: a.prompt.slice(0, 50) || "（无 prompt）",
|
||||||
|
sublabel: new Date(a.createdAt).toLocaleString("zh-CN"),
|
||||||
|
thumb: a.url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if (kind === "all" || kind === "character") {
|
||||||
|
for (const c of characters) {
|
||||||
|
if (q && !c.name.toLowerCase().includes(q) && !c.id.includes(q)) continue;
|
||||||
|
out.push({
|
||||||
|
id: c.id,
|
||||||
|
kind: "character",
|
||||||
|
label: c.name,
|
||||||
|
sublabel: c.visualHooks.slice(0, 3).join(" · "),
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if (kind === "all" || kind === "style") {
|
||||||
|
for (const s of stylePacks) {
|
||||||
|
if (q && !s.name.toLowerCase().includes(q) && !s.id.includes(q)) continue;
|
||||||
|
out.push({
|
||||||
|
id: s.id,
|
||||||
|
kind: "style",
|
||||||
|
label: s.name,
|
||||||
|
sublabel: s.keywords.slice(0, 3).join(" · "),
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return out.slice(0, 40);
|
||||||
|
}, [assets, characters, stylePacks, kind, query]);
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div
|
||||||
|
className="fixed inset-0 z-[60] flex items-start justify-center pt-[15vh] bg-black/30 backdrop-blur-sm"
|
||||||
|
onClick={onClose}
|
||||||
|
>
|
||||||
|
<div
|
||||||
|
className="surface-3 rounded-xl w-full max-w-xl mx-4 overflow-hidden flex flex-col"
|
||||||
|
onClick={(e) => e.stopPropagation()}
|
||||||
|
>
|
||||||
|
{/* 搜索框 */}
|
||||||
|
<div className="flex items-center gap-2 px-3 py-2 border-b border-[var(--border)]">
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="var(--text-secondary)" strokeWidth="2">
|
||||||
|
<circle cx="12" cy="12" r="4" />
|
||||||
|
<path d="M16 8v5a3 3 0 0 0 6 0v-1a10 10 0 1 0-4 8" />
|
||||||
|
</svg>
|
||||||
|
<input
|
||||||
|
ref={inputRef}
|
||||||
|
value={query}
|
||||||
|
onChange={(e) => setQuery(e.target.value)}
|
||||||
|
placeholder="引用资产：图片 / 角色 / 风格..."
|
||||||
|
className="flex-1 bg-transparent border-none outline-none text-sm
|
||||||
|
text-[var(--text-primary)] placeholder:text-[var(--text-secondary)]"
|
||||||
|
/>
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)] bg-[var(--bg-tertiary)] px-1.5 py-0.5 rounded border border-[var(--border)]">
|
||||||
|
Esc 关闭
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 类型切换 */}
|
||||||
|
<div className="flex items-center gap-1 px-3 py-2 border-b border-[var(--border)]">
|
||||||
|
{([
|
||||||
|
{ k: "all", label: "全部" },
|
||||||
|
{ k: "image", label: "图片" },
|
||||||
|
{ k: "character", label: "角色" },
|
||||||
|
{ k: "style", label: "风格" },
|
||||||
|
] as const).map((t) => (
|
||||||
|
<button
|
||||||
|
key={t.k}
|
||||||
|
onClick={() => setKind(t.k)}
|
||||||
|
className={`px-2.5 py-1 text-[11px] rounded-md cursor-pointer transition-all ${
|
||||||
|
kind === t.k
|
||||||
|
? "bg-[var(--accent)]/12 text-[var(--accent)] border border-[var(--accent)]/30"
|
||||||
|
: "border border-[var(--border)] text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{t.label}
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 结果列表 */}
|
||||||
|
<div className="max-h-[50vh] overflow-y-auto">
|
||||||
|
{results.length === 0 ? (
|
||||||
|
<div className="py-8 text-center text-xs text-[var(--text-secondary)]">
|
||||||
|
没有匹配的资产
|
||||||
|
</div>
|
||||||
|
) : (
|
||||||
|
results.map((r) => (
|
||||||
|
<button
|
||||||
|
key={`${r.kind}-${r.id}`}
|
||||||
|
onClick={() => onInsert(`[[asset:${r.id}]]`)}
|
||||||
|
className="w-full px-3 py-2 flex items-center gap-2.5 text-left cursor-pointer
|
||||||
|
hover:bg-[var(--accent)]/5 transition-colors border-b border-[var(--border)] last:border-0"
|
||||||
|
>
|
||||||
|
{r.kind === "image" && r.thumb ? (
|
||||||
|
<img
|
||||||
|
src={getImageUrl(r.thumb)}
|
||||||
|
alt=""
|
||||||
|
className="w-9 h-9 rounded-md object-cover border border-[var(--border)] flex-shrink-0"
|
||||||
|
/>
|
||||||
|
) : (
|
||||||
|
<div
|
||||||
|
className={`w-9 h-9 rounded-md border border-[var(--border)] flex-shrink-0
|
||||||
|
flex items-center justify-center ${
|
||||||
|
r.kind === "character"
|
||||||
|
? "bg-[var(--accent)]/10 text-[var(--accent)]"
|
||||||
|
: "bg-gradient-to-br from-[var(--accent)]/20 to-[var(--accent-secondary)]/20 text-[var(--accent-secondary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{r.kind === "character" ? (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<circle cx="12" cy="8" r="4" />
|
||||||
|
<path d="M4 21a8 8 0 0 1 16 0" />
|
||||||
|
</svg>
|
||||||
|
) : (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<circle cx="12" cy="12" r="9" />
|
||||||
|
<circle cx="12" cy="12" r="3" />
|
||||||
|
</svg>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
<div className="flex-1 min-w-0">
|
||||||
|
<div className="flex items-center gap-1.5">
|
||||||
|
<span className="typo-micro text-[9px]" style={{ textTransform: "none" }}>
|
||||||
|
{r.kind === "image" ? "图片" : r.kind === "character" ? "角色" : "风格"}
|
||||||
|
</span>
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)] font-mono truncate">
|
||||||
|
{r.id}
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
<div className="text-xs text-[var(--text-primary)] truncate">{r.label}</div>
|
||||||
|
{r.sublabel && (
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)] truncate">
|
||||||
|
{r.sublabel}
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
</button>
|
||||||
|
))
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div className="px-3 py-1.5 text-[10px] text-[var(--text-secondary)]
|
||||||
|
bg-[var(--bg-secondary)]/40 border-t border-[var(--border)]">
|
||||||
|
选中后以 <code className="font-mono text-[var(--accent)]">[[asset:id]]</code> 形式插入
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
494
art-agent/frontend/src/components/docs/command-palette.tsx
Normal file
494
art-agent/frontend/src/components/docs/command-palette.tsx
Normal file
@@ -0,0 +1,494 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useState, useEffect, useRef, useMemo } from "react";
|
||||||
|
import { useRouter } from "next/navigation";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import type { DocNode } from "@/lib/types";
|
||||||
|
import { getImageUrl } from "@/lib/api";
|
||||||
|
|
||||||
|
type CommandItem =
|
||||||
|
| { id: string; kind: "nav"; label: string; hint: string; action: () => void; icon: React.ReactNode }
|
||||||
|
| { id: string; kind: "action"; label: string; hint: string; action: () => void; icon: React.ReactNode }
|
||||||
|
| { id: string; kind: "doc"; label: string; hint: string; action: () => void; icon: React.ReactNode }
|
||||||
|
| { id: string; kind: "asset"; label: string; hint: string; action: () => void; icon: React.ReactNode; thumb?: string }
|
||||||
|
| { id: string; kind: "char"; label: string; hint: string; action: () => void; icon: React.ReactNode }
|
||||||
|
| { id: string; kind: "style"; label: string; hint: string; action: () => void; icon: React.ReactNode }
|
||||||
|
| { id: string; kind: "session"; label: string; hint: string; action: () => void; icon: React.ReactNode };
|
||||||
|
|
||||||
|
const KIND_META: Record<CommandItem["kind"], { label: string; color: string }> = {
|
||||||
|
nav: { label: "导航", color: "var(--accent)" },
|
||||||
|
action: { label: "操作", color: "var(--accent-secondary)" },
|
||||||
|
doc: { label: "文档", color: "var(--accent)" },
|
||||||
|
asset: { label: "图片", color: "var(--gold)" },
|
||||||
|
char: { label: "角色", color: "var(--accent)" },
|
||||||
|
style: { label: "风格", color: "var(--accent-secondary)" },
|
||||||
|
session: { label: "会话", color: "var(--text-secondary)" },
|
||||||
|
};
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 全站命令面板（Ctrl/Cmd+K）
|
||||||
|
*
|
||||||
|
* 聚合：导航、全局操作、文档、资产、角色、风格、会话。
|
||||||
|
* 通过 app-context 中的 commandPaletteOpen 控制可见性。
|
||||||
|
*/
|
||||||
|
export function CommandPalette() {
|
||||||
|
const router = useRouter();
|
||||||
|
const {
|
||||||
|
commandPaletteOpen: open,
|
||||||
|
setCommandPaletteOpen: setOpen,
|
||||||
|
docs,
|
||||||
|
assets,
|
||||||
|
characters,
|
||||||
|
stylePacks,
|
||||||
|
sessions,
|
||||||
|
switchSession,
|
||||||
|
createSession,
|
||||||
|
setSessionTaskType,
|
||||||
|
} = useApp();
|
||||||
|
|
||||||
|
const [query, setQuery] = useState("");
|
||||||
|
const [activeIdx, setActiveIdx] = useState(0);
|
||||||
|
const inputRef = useRef<HTMLInputElement>(null);
|
||||||
|
const listRef = useRef<HTMLDivElement>(null);
|
||||||
|
|
||||||
|
// 全局快捷键：Cmd/Ctrl+K
|
||||||
|
useEffect(() => {
|
||||||
|
const handler = (e: KeyboardEvent) => {
|
||||||
|
if ((e.ctrlKey || e.metaKey) && e.key.toLowerCase() === "k") {
|
||||||
|
e.preventDefault();
|
||||||
|
setOpen(!open);
|
||||||
|
}
|
||||||
|
if (e.key === "Escape" && open) {
|
||||||
|
setOpen(false);
|
||||||
|
}
|
||||||
|
};
|
||||||
|
window.addEventListener("keydown", handler);
|
||||||
|
return () => window.removeEventListener("keydown", handler);
|
||||||
|
}, [open, setOpen]);
|
||||||
|
|
||||||
|
// 打开时聚焦输入框、重置状态
|
||||||
|
useEffect(() => {
|
||||||
|
if (open) {
|
||||||
|
setQuery("");
|
||||||
|
setActiveIdx(0);
|
||||||
|
requestAnimationFrame(() => inputRef.current?.focus());
|
||||||
|
}
|
||||||
|
}, [open]);
|
||||||
|
|
||||||
|
// 收集所有文档（扁平化）
|
||||||
|
const flatDocs = useMemo(() => {
|
||||||
|
const out: DocNode[] = [];
|
||||||
|
const walk = (list: DocNode[]) => {
|
||||||
|
for (const n of list) {
|
||||||
|
if (n.type === "doc") out.push(n);
|
||||||
|
if (n.children) walk(n.children);
|
||||||
|
}
|
||||||
|
};
|
||||||
|
walk(docs);
|
||||||
|
return out;
|
||||||
|
}, [docs]);
|
||||||
|
|
||||||
|
const items = useMemo<CommandItem[]>(() => {
|
||||||
|
const out: CommandItem[] = [
|
||||||
|
{
|
||||||
|
id: "nav-workbench",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 工作台",
|
||||||
|
hint: "/",
|
||||||
|
action: () => router.push("/"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "nav-docs",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 文档中心",
|
||||||
|
hint: "/docs",
|
||||||
|
action: () => router.push("/docs"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "nav-gallery",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 资源库",
|
||||||
|
hint: "/gallery",
|
||||||
|
action: () => router.push("/gallery"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "nav-styles",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 风格库",
|
||||||
|
hint: "/styles",
|
||||||
|
action: () => router.push("/styles"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "nav-chars",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 角色库",
|
||||||
|
hint: "/characters",
|
||||||
|
action: () => router.push("/characters"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "nav-training",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 训练中心",
|
||||||
|
hint: "/training",
|
||||||
|
action: () => router.push("/training"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "nav-settings",
|
||||||
|
kind: "nav",
|
||||||
|
label: "前往 · 项目设置",
|
||||||
|
hint: "/settings",
|
||||||
|
action: () => router.push("/settings"),
|
||||||
|
icon: <IconDot />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "action-new-session",
|
||||||
|
kind: "action",
|
||||||
|
label: "新建对话",
|
||||||
|
hint: "工作台",
|
||||||
|
action: () => {
|
||||||
|
createSession();
|
||||||
|
router.push("/");
|
||||||
|
},
|
||||||
|
icon: <IconPlus />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "action-switch-2d",
|
||||||
|
kind: "action",
|
||||||
|
label: "切换任务类型 · 2D 图片",
|
||||||
|
hint: "工作台",
|
||||||
|
action: () => {
|
||||||
|
setSessionTaskType("image2d");
|
||||||
|
router.push("/");
|
||||||
|
},
|
||||||
|
icon: <IconSwitch />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "action-switch-3d",
|
||||||
|
kind: "action",
|
||||||
|
label: "切换任务类型 · 3D 模型",
|
||||||
|
hint: "工作台",
|
||||||
|
action: () => {
|
||||||
|
setSessionTaskType("model3d");
|
||||||
|
router.push("/");
|
||||||
|
},
|
||||||
|
icon: <IconSwitch />,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "action-switch-motion",
|
||||||
|
kind: "action",
|
||||||
|
label: "切换任务类型 · 动作序列",
|
||||||
|
hint: "工作台",
|
||||||
|
action: () => {
|
||||||
|
setSessionTaskType("motion");
|
||||||
|
router.push("/");
|
||||||
|
},
|
||||||
|
icon: <IconSwitch />,
|
||||||
|
},
|
||||||
|
];
|
||||||
|
for (const d of flatDocs) {
|
||||||
|
out.push({
|
||||||
|
id: `doc-${d.id}`,
|
||||||
|
kind: "doc",
|
||||||
|
label: d.name,
|
||||||
|
hint: (d.content ?? "").replace(/\n/g, " ").slice(0, 80) || "（空文档）",
|
||||||
|
action: () => router.push("/docs"),
|
||||||
|
icon: <IconDoc />,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
for (const a of assets.slice(0, 50)) {
|
||||||
|
out.push({
|
||||||
|
id: `asset-${a.id}`,
|
||||||
|
kind: "asset",
|
||||||
|
label: a.prompt.slice(0, 60) || "（无 prompt）",
|
||||||
|
hint: new Date(a.createdAt).toLocaleString("zh-CN"),
|
||||||
|
action: () => router.push("/gallery"),
|
||||||
|
icon: <IconImage />,
|
||||||
|
thumb: a.url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
for (const c of characters) {
|
||||||
|
out.push({
|
||||||
|
id: `char-${c.id}`,
|
||||||
|
kind: "char",
|
||||||
|
label: c.name,
|
||||||
|
hint: c.visualHooks.slice(0, 3).join(" · "),
|
||||||
|
action: () => router.push(`/characters/${c.id}`),
|
||||||
|
icon: <IconChar />,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
for (const s of stylePacks) {
|
||||||
|
out.push({
|
||||||
|
id: `style-${s.id}`,
|
||||||
|
kind: "style",
|
||||||
|
label: s.name,
|
||||||
|
hint: s.keywords.slice(0, 3).join(" · "),
|
||||||
|
action: () => router.push(`/styles/${s.id}`),
|
||||||
|
icon: <IconStyle />,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
for (const s of sessions.slice(0, 20)) {
|
||||||
|
out.push({
|
||||||
|
id: `session-${s.id}`,
|
||||||
|
kind: "session",
|
||||||
|
label: s.title || "未命名会话",
|
||||||
|
hint: new Date(s.updatedAt).toLocaleString("zh-CN"),
|
||||||
|
action: () => {
|
||||||
|
switchSession(s.id);
|
||||||
|
router.push("/");
|
||||||
|
},
|
||||||
|
icon: <IconSession />,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
return out;
|
||||||
|
}, [flatDocs, assets, characters, stylePacks, sessions, router, createSession, switchSession, setSessionTaskType]);
|
||||||
|
|
||||||
|
const filtered = useMemo(() => {
|
||||||
|
if (!query.trim()) {
|
||||||
|
return items.slice(0, 30);
|
||||||
|
}
|
||||||
|
const q = query.toLowerCase();
|
||||||
|
const tokens = q.split(/\s+/).filter(Boolean);
|
||||||
|
return items
|
||||||
|
.map((it) => {
|
||||||
|
const haystack = `${it.label} ${it.hint} ${KIND_META[it.kind].label}`.toLowerCase();
|
||||||
|
let score = 0;
|
||||||
|
for (const t of tokens) {
|
||||||
|
const pos = haystack.indexOf(t);
|
||||||
|
if (pos < 0) return null;
|
||||||
|
score += 1 - pos / 200;
|
||||||
|
}
|
||||||
|
return { it, score };
|
||||||
|
})
|
||||||
|
.filter((x): x is { it: CommandItem; score: number } => x !== null)
|
||||||
|
.sort((a, b) => b.score - a.score)
|
||||||
|
.slice(0, 50)
|
||||||
|
.map((x) => x.it);
|
||||||
|
}, [items, query]);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
setActiveIdx(0);
|
||||||
|
}, [query]);
|
||||||
|
|
||||||
|
// 滚动选中项到可见
|
||||||
|
useEffect(() => {
|
||||||
|
if (!listRef.current) return;
|
||||||
|
const el = listRef.current.querySelector<HTMLElement>(`[data-idx="${activeIdx}"]`);
|
||||||
|
el?.scrollIntoView({ block: "nearest" });
|
||||||
|
}, [activeIdx]);
|
||||||
|
|
||||||
|
if (!open) return null;
|
||||||
|
|
||||||
|
const handleKeyDown = (e: React.KeyboardEvent<HTMLInputElement>) => {
|
||||||
|
if (e.key === "ArrowDown") {
|
||||||
|
e.preventDefault();
|
||||||
|
setActiveIdx((i) => Math.min(filtered.length - 1, i + 1));
|
||||||
|
} else if (e.key === "ArrowUp") {
|
||||||
|
e.preventDefault();
|
||||||
|
setActiveIdx((i) => Math.max(0, i - 1));
|
||||||
|
} else if (e.key === "Enter") {
|
||||||
|
e.preventDefault();
|
||||||
|
const it = filtered[activeIdx];
|
||||||
|
if (it) {
|
||||||
|
it.action();
|
||||||
|
setOpen(false);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div
|
||||||
|
className="fixed inset-0 z-[70] flex items-start justify-center pt-[12vh] bg-black/40 backdrop-blur-sm"
|
||||||
|
onClick={() => setOpen(false)}
|
||||||
|
>
|
||||||
|
<div
|
||||||
|
className="surface-3 rounded-xl w-full max-w-2xl mx-4 overflow-hidden flex flex-col shadow-2xl"
|
||||||
|
onClick={(e) => e.stopPropagation()}
|
||||||
|
>
|
||||||
|
{/* 搜索框 */}
|
||||||
|
<div className="flex items-center gap-2 px-4 py-3 border-b border-[var(--border)]">
|
||||||
|
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="var(--accent)" strokeWidth="2">
|
||||||
|
<circle cx="11" cy="11" r="8" />
|
||||||
|
<path d="M21 21l-4.35-4.35" />
|
||||||
|
</svg>
|
||||||
|
<input
|
||||||
|
ref={inputRef}
|
||||||
|
value={query}
|
||||||
|
onChange={(e) => setQuery(e.target.value)}
|
||||||
|
onKeyDown={handleKeyDown}
|
||||||
|
placeholder="搜索页面、操作、文档、资产、角色、风格、会话..."
|
||||||
|
className="flex-1 bg-transparent border-none outline-none text-sm
|
||||||
|
text-[var(--text-primary)] placeholder:text-[var(--text-secondary)]"
|
||||||
|
/>
|
||||||
|
<div className="flex items-center gap-1 text-[10px] text-[var(--text-secondary)]">
|
||||||
|
<Kbd>↑↓</Kbd>
|
||||||
|
<Kbd>Enter</Kbd>
|
||||||
|
<Kbd>Esc</Kbd>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 结果列表 */}
|
||||||
|
<div ref={listRef} className="max-h-[55vh] overflow-y-auto">
|
||||||
|
{filtered.length === 0 ? (
|
||||||
|
<div className="py-10 text-center text-xs text-[var(--text-secondary)]">
|
||||||
|
没有匹配的结果
|
||||||
|
</div>
|
||||||
|
) : (
|
||||||
|
filtered.map((it, i) => {
|
||||||
|
const meta = KIND_META[it.kind];
|
||||||
|
const active = i === activeIdx;
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
key={it.id}
|
||||||
|
data-idx={i}
|
||||||
|
onMouseMove={() => setActiveIdx(i)}
|
||||||
|
onClick={() => {
|
||||||
|
it.action();
|
||||||
|
setOpen(false);
|
||||||
|
}}
|
||||||
|
className={`w-full px-4 py-2 flex items-center gap-3 text-left cursor-pointer transition-colors ${
|
||||||
|
active
|
||||||
|
? "bg-[var(--accent)]/10"
|
||||||
|
: "hover:bg-[var(--accent)]/5"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
<div
|
||||||
|
className="flex-shrink-0 w-8 h-8 rounded-md flex items-center justify-center
|
||||||
|
border border-[var(--border)]"
|
||||||
|
style={{ color: meta.color, backgroundColor: meta.color + "12" }}
|
||||||
|
>
|
||||||
|
{it.kind === "asset" && "thumb" in it && it.thumb ? (
|
||||||
|
<img
|
||||||
|
src={getImageUrl(it.thumb)}
|
||||||
|
alt=""
|
||||||
|
className="w-full h-full object-cover rounded-md"
|
||||||
|
/>
|
||||||
|
) : (
|
||||||
|
it.icon
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
<div className="flex-1 min-w-0">
|
||||||
|
<div className="flex items-center gap-1.5">
|
||||||
|
<span
|
||||||
|
className="text-[9px] font-semibold px-1.5 py-0.5 rounded"
|
||||||
|
style={{ color: meta.color, backgroundColor: meta.color + "12" }}
|
||||||
|
>
|
||||||
|
{meta.label}
|
||||||
|
</span>
|
||||||
|
<span
|
||||||
|
className={`text-xs truncate ${
|
||||||
|
active ? "text-[var(--accent)]" : "text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{it.label}
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)] truncate">
|
||||||
|
{it.hint}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
{active && (
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="var(--accent)" strokeWidth="2.5" className="flex-shrink-0">
|
||||||
|
<path d="M9 18l6-6-6-6" />
|
||||||
|
</svg>
|
||||||
|
)}
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
})
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div className="px-4 py-2 border-t border-[var(--border)] bg-[var(--bg-secondary)]/40
|
||||||
|
text-[10px] text-[var(--text-secondary)] flex items-center gap-3">
|
||||||
|
<span>EPEEKit 命令面板</span>
|
||||||
|
<span>·</span>
|
||||||
|
<span>{filtered.length} 条结果</span>
|
||||||
|
<div className="flex-1" />
|
||||||
|
<span>
|
||||||
|
按 <Kbd>Ctrl</Kbd>+<Kbd>K</Kbd> 随时唤起
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function Kbd({ children }: { children: React.ReactNode }) {
|
||||||
|
return (
|
||||||
|
<kbd className="px-1 py-0.5 rounded bg-[var(--bg-tertiary)] border border-[var(--border)]
|
||||||
|
text-[9px] font-mono text-[var(--text-secondary)]">
|
||||||
|
{children}
|
||||||
|
</kbd>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function IconDot() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor">
|
||||||
|
<circle cx="12" cy="12" r="5" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconPlus() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<line x1="12" y1="5" x2="12" y2="19" />
|
||||||
|
<line x1="5" y1="12" x2="19" y2="12" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconSwitch() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polyline points="17 1 21 5 17 9" />
|
||||||
|
<path d="M3 11V9a4 4 0 0 1 4-4h14" />
|
||||||
|
<polyline points="7 23 3 19 7 15" />
|
||||||
|
<path d="M21 13v2a4 4 0 0 1-4 4H3" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconDoc() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconImage() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<circle cx="8.5" cy="8.5" r="1.5" />
|
||||||
|
<polyline points="21 15 16 10 5 21" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconChar() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<circle cx="12" cy="8" r="4" />
|
||||||
|
<path d="M4 21a8 8 0 0 1 16 0" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconStyle() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<circle cx="12" cy="12" r="9" strokeDasharray="2 3" />
|
||||||
|
<circle cx="12" cy="12" r="3" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
function IconSession() {
|
||||||
|
return (
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M21 15a2 2 0 01-2 2H7l-4 4V5a2 2 0 012-2h14a2 2 0 012 2z" />
|
||||||
|
</svg>
|
||||||
|
);
|
||||||
|
}
|
||||||
315
art-agent/frontend/src/components/docs/doc-editor.tsx
Normal file
315
art-agent/frontend/src/components/docs/doc-editor.tsx
Normal file
@@ -0,0 +1,315 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useRef, useState, useEffect } from "react";
|
||||||
|
import type { DocNode } from "@/lib/types";
|
||||||
|
import { AssetPicker } from "./asset-picker";
|
||||||
|
import { MarkdownContent } from "./markdown-content";
|
||||||
|
|
||||||
|
type ViewMode = "source" | "preview" | "split";
|
||||||
|
|
||||||
|
interface DocEditorProps {
|
||||||
|
doc: DocNode;
|
||||||
|
/** 当前 buffer，可能包含未保存修改 */
|
||||||
|
buffer: string;
|
||||||
|
onChange: (content: string) => void;
|
||||||
|
onSave: () => void;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function DocEditor({ doc, buffer, onChange, onSave }: DocEditorProps) {
|
||||||
|
const [viewMode, setViewMode] = useState<ViewMode>("split");
|
||||||
|
const [assetPickerOpen, setAssetPickerOpen] = useState(false);
|
||||||
|
const textareaRef = useRef<HTMLTextAreaElement>(null);
|
||||||
|
|
||||||
|
// Ctrl+S 保存
|
||||||
|
useEffect(() => {
|
||||||
|
const handler = (e: KeyboardEvent) => {
|
||||||
|
if ((e.ctrlKey || e.metaKey) && e.key === "s") {
|
||||||
|
e.preventDefault();
|
||||||
|
onSave();
|
||||||
|
}
|
||||||
|
};
|
||||||
|
window.addEventListener("keydown", handler);
|
||||||
|
return () => window.removeEventListener("keydown", handler);
|
||||||
|
}, [onSave]);
|
||||||
|
|
||||||
|
const insertAtCursor = (before: string, after = "") => {
|
||||||
|
const ta = textareaRef.current;
|
||||||
|
if (!ta) return;
|
||||||
|
const start = ta.selectionStart;
|
||||||
|
const end = ta.selectionEnd;
|
||||||
|
const selected = buffer.slice(start, end);
|
||||||
|
const next = buffer.slice(0, start) + before + selected + after + buffer.slice(end);
|
||||||
|
onChange(next);
|
||||||
|
requestAnimationFrame(() => {
|
||||||
|
ta.focus();
|
||||||
|
const pos = start + before.length + selected.length;
|
||||||
|
ta.setSelectionRange(pos, pos);
|
||||||
|
});
|
||||||
|
};
|
||||||
|
|
||||||
|
const insertLine = (prefix: string) => {
|
||||||
|
const ta = textareaRef.current;
|
||||||
|
if (!ta) return;
|
||||||
|
const start = ta.selectionStart;
|
||||||
|
const lineStart = buffer.lastIndexOf("\n", start - 1) + 1;
|
||||||
|
const next = buffer.slice(0, lineStart) + prefix + buffer.slice(lineStart);
|
||||||
|
onChange(next);
|
||||||
|
requestAnimationFrame(() => {
|
||||||
|
ta.focus();
|
||||||
|
ta.setSelectionRange(start + prefix.length, start + prefix.length);
|
||||||
|
});
|
||||||
|
};
|
||||||
|
|
||||||
|
const handleInsertAsset = (assetRef: string) => {
|
||||||
|
insertAtCursor(assetRef);
|
||||||
|
setAssetPickerOpen(false);
|
||||||
|
};
|
||||||
|
|
||||||
|
// 监听 @ 键唤起资产选择器
|
||||||
|
const handleKeyDown = (e: React.KeyboardEvent<HTMLTextAreaElement>) => {
|
||||||
|
if (e.key === "@") {
|
||||||
|
e.preventDefault();
|
||||||
|
setAssetPickerOpen(true);
|
||||||
|
}
|
||||||
|
if (e.key === "Tab") {
|
||||||
|
e.preventDefault();
|
||||||
|
insertAtCursor(" ");
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
const stats = {
|
||||||
|
chars: buffer.length,
|
||||||
|
lines: buffer.split("\n").length,
|
||||||
|
words: buffer.trim() ? buffer.trim().split(/\s+/).length : 0,
|
||||||
|
};
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="flex-1 flex flex-col min-h-0">
|
||||||
|
{/* 工具条 */}
|
||||||
|
<div className="flex-shrink-0 border-b border-[var(--border)] px-3 py-2
|
||||||
|
flex items-center gap-1 flex-wrap bg-[var(--bg-secondary)]/40 backdrop-blur-sm">
|
||||||
|
<ToolBtn onClick={() => insertLine("# ")} title="H1">
|
||||||
|
<span className="text-[11px] font-bold">H1</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertLine("## ")} title="H2">
|
||||||
|
<span className="text-[11px] font-bold">H2</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertLine("### ")} title="H3">
|
||||||
|
<span className="text-[11px] font-bold">H3</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<Sep />
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("**", "**")} title="粗体（Ctrl+B）">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<path d="M6 4h8a4 4 0 0 1 4 4 4 4 0 0 1-4 4H6zM6 12h9a4 4 0 0 1 4 4 4 4 0 0 1-4 4H6z" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("*", "*")} title="斜体">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<line x1="19" y1="4" x2="10" y2="4" />
|
||||||
|
<line x1="14" y1="20" x2="5" y2="20" />
|
||||||
|
<line x1="15" y1="4" x2="9" y2="20" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("~~", "~~")} title="删除线">
|
||||||
|
<span className="text-[11px] line-through">S</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<Sep />
|
||||||
|
<ToolBtn onClick={() => insertLine("- ")} title="无序列表">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<line x1="8" y1="6" x2="21" y2="6" />
|
||||||
|
<line x1="8" y1="12" x2="21" y2="12" />
|
||||||
|
<line x1="8" y1="18" x2="21" y2="18" />
|
||||||
|
<circle cx="3.5" cy="6" r="1" />
|
||||||
|
<circle cx="3.5" cy="12" r="1" />
|
||||||
|
<circle cx="3.5" cy="18" r="1" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertLine("1. ")} title="有序列表">
|
||||||
|
<span className="text-[10px] font-mono">1.</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertLine("> ")} title="引用">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M3 21c3 0 7-1 7-8V5c0-1.25-.756-2.017-2-2H4c-1.25 0-2 .75-2 1.972V11c0 1.25.75 2 2 2 1 0 1 0 1 1v1c0 1-1 2-2 2s-1 .008-1 1.031V20c0 1 0 1 1 1z" />
|
||||||
|
<path d="M15 21c3 0 7-1 7-8V5c0-1.25-.757-2.017-2-2h-4c-1.25 0-2 .75-2 1.972V11c0 1.25.75 2 2 2h.75c0 2.25.25 4-2.75 4v3c0 1 0 1 1 1z" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("`", "`")} title="行内代码">
|
||||||
|
<span className="text-[11px] font-mono">{"<>"}</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("\n```\n", "\n```\n")} title="代码块">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polyline points="16 18 22 12 16 6" />
|
||||||
|
<polyline points="8 6 2 12 8 18" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<Sep />
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("[", "](url)")} title="链接">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71" />
|
||||||
|
<path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.72-1.71" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("![alt](", ")")} title="图片">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
|
||||||
|
<circle cx="8.5" cy="8.5" r="1.5" />
|
||||||
|
<polyline points="21 15 16 10 5 21" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn onClick={() => setAssetPickerOpen(true)} title="引用资产（@）">
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<circle cx="12" cy="12" r="4" />
|
||||||
|
<path d="M16 8v5a3 3 0 0 0 6 0v-1a10 10 0 1 0-4 8" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
<Sep />
|
||||||
|
<ToolBtn onClick={() => insertAtCursor("\n---\n")} title="分割线">
|
||||||
|
<span className="text-[11px] font-mono">—</span>
|
||||||
|
</ToolBtn>
|
||||||
|
<ToolBtn
|
||||||
|
onClick={() =>
|
||||||
|
insertAtCursor("\n| 列 1 | 列 2 |\n|---|---|\n| A | B |\n")
|
||||||
|
}
|
||||||
|
title="表格"
|
||||||
|
>
|
||||||
|
<svg width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<line x1="3" y1="9" x2="21" y2="9" />
|
||||||
|
<line x1="3" y1="15" x2="21" y2="15" />
|
||||||
|
<line x1="12" y1="3" x2="12" y2="21" />
|
||||||
|
</svg>
|
||||||
|
</ToolBtn>
|
||||||
|
|
||||||
|
<div className="flex-1" />
|
||||||
|
|
||||||
|
{/* 视图切换 */}
|
||||||
|
<div className="flex items-center bg-[var(--bg-tertiary)] rounded-md p-0.5 border border-[var(--border)]">
|
||||||
|
<ViewBtn active={viewMode === "source"} onClick={() => setViewMode("source")} title="源码">
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polyline points="16 18 22 12 16 6" />
|
||||||
|
<polyline points="8 6 2 12 8 18" />
|
||||||
|
</svg>
|
||||||
|
</ViewBtn>
|
||||||
|
<ViewBtn active={viewMode === "split"} onClick={() => setViewMode("split")} title="分栏">
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<rect x="3" y="3" width="18" height="18" rx="2" />
|
||||||
|
<line x1="12" y1="3" x2="12" y2="21" />
|
||||||
|
</svg>
|
||||||
|
</ViewBtn>
|
||||||
|
<ViewBtn active={viewMode === "preview"} onClick={() => setViewMode("preview")} title="预览">
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M1 12s4-8 11-8 11 8 11 8-4 8-11 8-11-8-11-8z" />
|
||||||
|
<circle cx="12" cy="12" r="3" />
|
||||||
|
</svg>
|
||||||
|
</ViewBtn>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<button
|
||||||
|
onClick={onSave}
|
||||||
|
className="ml-1 h-7 px-3 rounded-md text-xs font-medium bg-[var(--accent)] text-white
|
||||||
|
hover:bg-[var(--accent-hover)] cursor-pointer transition-all"
|
||||||
|
title="保存（Ctrl+S）"
|
||||||
|
>
|
||||||
|
保存
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 编辑/预览区 */}
|
||||||
|
<div className="flex-1 min-h-0 flex overflow-hidden">
|
||||||
|
{(viewMode === "source" || viewMode === "split") && (
|
||||||
|
<div className="flex-1 min-w-0 relative">
|
||||||
|
<textarea
|
||||||
|
ref={textareaRef}
|
||||||
|
value={buffer}
|
||||||
|
onChange={(e) => onChange(e.target.value)}
|
||||||
|
onKeyDown={handleKeyDown}
|
||||||
|
spellCheck={false}
|
||||||
|
className="w-full h-full px-5 py-4 bg-transparent border-none outline-none resize-none
|
||||||
|
text-sm leading-relaxed text-[var(--text-primary)]
|
||||||
|
font-mono placeholder:text-[var(--text-secondary)]"
|
||||||
|
placeholder={`# ${doc.name.replace(/\.md$/, "")}\n\n开始写吧。按 @ 键可快速引用资产。`}
|
||||||
|
/>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
{viewMode === "split" && (
|
||||||
|
<div className="w-px bg-[var(--border)] flex-shrink-0" />
|
||||||
|
)}
|
||||||
|
{(viewMode === "preview" || viewMode === "split") && (
|
||||||
|
<div className="flex-1 min-w-0 overflow-y-auto px-6 py-5 fog-scroll">
|
||||||
|
<MarkdownContent content={buffer} />
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 状态栏 */}
|
||||||
|
<div className="flex-shrink-0 border-t border-[var(--border)] px-4 py-1.5
|
||||||
|
flex items-center gap-4 text-[10px] text-[var(--text-secondary)]
|
||||||
|
bg-[var(--bg-secondary)]/40">
|
||||||
|
<span>{doc.name}</span>
|
||||||
|
<span>·</span>
|
||||||
|
<span>{stats.chars} 字符</span>
|
||||||
|
<span>·</span>
|
||||||
|
<span>{stats.lines} 行</span>
|
||||||
|
<span>·</span>
|
||||||
|
<span>{stats.words} 词</span>
|
||||||
|
<div className="flex-1" />
|
||||||
|
<span>Markdown</span>
|
||||||
|
<span>·</span>
|
||||||
|
<span>UTF-8</span>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{assetPickerOpen && (
|
||||||
|
<AssetPicker onInsert={handleInsertAsset} onClose={() => setAssetPickerOpen(false)} />
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function ToolBtn({
|
||||||
|
onClick,
|
||||||
|
children,
|
||||||
|
title,
|
||||||
|
}: {
|
||||||
|
onClick: () => void;
|
||||||
|
children: React.ReactNode;
|
||||||
|
title: string;
|
||||||
|
}) {
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
onClick={onClick}
|
||||||
|
title={title}
|
||||||
|
className="w-7 h-7 rounded-md flex items-center justify-center cursor-pointer transition-all
|
||||||
|
text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:bg-[var(--accent)]/8"
|
||||||
|
>
|
||||||
|
{children}
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function ViewBtn({
|
||||||
|
active,
|
||||||
|
onClick,
|
||||||
|
children,
|
||||||
|
title,
|
||||||
|
}: {
|
||||||
|
active: boolean;
|
||||||
|
onClick: () => void;
|
||||||
|
children: React.ReactNode;
|
||||||
|
title: string;
|
||||||
|
}) {
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
onClick={onClick}
|
||||||
|
title={title}
|
||||||
|
className={`w-7 h-6 rounded flex items-center justify-center cursor-pointer transition-all
|
||||||
|
${active ? "bg-[var(--accent)]/12 text-[var(--accent)]" : "text-[var(--text-secondary)] hover:text-[var(--text-primary)]"}`}
|
||||||
|
>
|
||||||
|
{children}
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function Sep() {
|
||||||
|
return <div className="w-px h-5 bg-[var(--border)] mx-0.5" />;
|
||||||
|
}
|
||||||
216
art-agent/frontend/src/components/docs/doc-outline.tsx
Normal file
216
art-agent/frontend/src/components/docs/doc-outline.tsx
Normal file
@@ -0,0 +1,216 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useMemo } from "react";
|
||||||
|
import Link from "next/link";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import { getImageUrl } from "@/lib/api";
|
||||||
|
|
||||||
|
interface DocOutlineProps {
|
||||||
|
content: string;
|
||||||
|
onJumpToLine?: (lineNo: number) => void;
|
||||||
|
}
|
||||||
|
|
||||||
|
interface Heading {
|
||||||
|
level: number;
|
||||||
|
text: string;
|
||||||
|
lineNo: number;
|
||||||
|
slug: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function DocOutline({ content, onJumpToLine }: DocOutlineProps) {
|
||||||
|
const { assets, characters, stylePacks } = useApp();
|
||||||
|
|
||||||
|
const headings = useMemo<Heading[]>(() => {
|
||||||
|
const out: Heading[] = [];
|
||||||
|
const lines = content.split("\n");
|
||||||
|
let inCodeBlock = false;
|
||||||
|
lines.forEach((line, i) => {
|
||||||
|
if (line.trim().startsWith("```")) {
|
||||||
|
inCodeBlock = !inCodeBlock;
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
if (inCodeBlock) return;
|
||||||
|
const m = line.match(/^(#{1,6})\s+(.+)$/);
|
||||||
|
if (m) {
|
||||||
|
out.push({
|
||||||
|
level: m[1].length,
|
||||||
|
text: m[2].trim(),
|
||||||
|
lineNo: i + 1,
|
||||||
|
slug: m[2].trim().toLowerCase().replace(/[^\w\u4e00-\u9fa5]+/g, "-"),
|
||||||
|
});
|
||||||
|
}
|
||||||
|
});
|
||||||
|
return out;
|
||||||
|
}, [content]);
|
||||||
|
|
||||||
|
const referencedAssets = useMemo(() => {
|
||||||
|
const ids = new Set<string>();
|
||||||
|
const re = /\[\[asset:([^\]]+)\]\]/g;
|
||||||
|
let m: RegExpExecArray | null;
|
||||||
|
while ((m = re.exec(content)) !== null) {
|
||||||
|
ids.add(m[1]);
|
||||||
|
}
|
||||||
|
return Array.from(ids)
|
||||||
|
.map((id) => {
|
||||||
|
const img = assets.find((a) => a.id === id);
|
||||||
|
const char = characters.find((c) => c.id === id);
|
||||||
|
const style = stylePacks.find((s) => s.id === id);
|
||||||
|
return { id, img, char, style };
|
||||||
|
});
|
||||||
|
}, [content, assets, characters, stylePacks]);
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="h-full flex flex-col">
|
||||||
|
{/* 大纲 */}
|
||||||
|
<div className="flex-shrink-0 px-3 pt-3 pb-2 border-b border-[var(--border)] flex items-center gap-2">
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="var(--accent)" strokeWidth="2">
|
||||||
|
<line x1="8" y1="6" x2="21" y2="6" />
|
||||||
|
<line x1="8" y1="12" x2="21" y2="12" />
|
||||||
|
<line x1="8" y1="18" x2="21" y2="18" />
|
||||||
|
<line x1="3" y1="6" x2="3.01" y2="6" />
|
||||||
|
<line x1="3" y1="12" x2="3.01" y2="12" />
|
||||||
|
<line x1="3" y1="18" x2="3.01" y2="18" />
|
||||||
|
</svg>
|
||||||
|
<span className="typo-strong text-xs flex-1">大纲</span>
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)]">{headings.length}</span>
|
||||||
|
</div>
|
||||||
|
<div className="flex-1 min-h-0 overflow-y-auto py-1.5">
|
||||||
|
{headings.length === 0 ? (
|
||||||
|
<div className="px-3 py-4 text-[11px] text-[var(--text-secondary)] text-center">
|
||||||
|
无标题
|
||||||
|
</div>
|
||||||
|
) : (
|
||||||
|
headings.map((h, i) => (
|
||||||
|
<button
|
||||||
|
key={`${h.lineNo}-${i}`}
|
||||||
|
onClick={() => onJumpToLine?.(h.lineNo)}
|
||||||
|
className="w-full text-left px-3 py-1 text-xs cursor-pointer
|
||||||
|
text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:bg-[var(--accent)]/5 transition-colors truncate"
|
||||||
|
style={{ paddingLeft: 12 + (h.level - 1) * 12 }}
|
||||||
|
title={h.text}
|
||||||
|
>
|
||||||
|
<span className="text-[9px] text-[var(--text-secondary)]/60 mr-1 font-mono">
|
||||||
|
H{h.level}
|
||||||
|
</span>
|
||||||
|
{h.text}
|
||||||
|
</button>
|
||||||
|
))
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 关联资产 */}
|
||||||
|
<div className="flex-shrink-0 border-t border-[var(--border)]">
|
||||||
|
<div className="px-3 pt-2.5 pb-1.5 flex items-center gap-2">
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="var(--accent)" strokeWidth="2">
|
||||||
|
<path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71" />
|
||||||
|
<path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.72-1.71" />
|
||||||
|
</svg>
|
||||||
|
<span className="typo-strong text-xs flex-1">关联资产</span>
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)]">{referencedAssets.length}</span>
|
||||||
|
</div>
|
||||||
|
<div className="max-h-[28vh] overflow-y-auto pb-2">
|
||||||
|
{referencedAssets.length === 0 ? (
|
||||||
|
<div className="px-3 py-3 text-[11px] text-[var(--text-secondary)] text-center">
|
||||||
|
文档中未引用任何资产
|
||||||
|
</div>
|
||||||
|
) : (
|
||||||
|
referencedAssets.map(({ id, img, char, style }) => {
|
||||||
|
const key = `${id}`;
|
||||||
|
if (img) {
|
||||||
|
return (
|
||||||
|
<div
|
||||||
|
key={key}
|
||||||
|
className="mx-2 my-1 p-1.5 flex items-center gap-2 rounded-md
|
||||||
|
border border-[var(--border)] hover:border-[var(--accent)]/40
|
||||||
|
bg-[var(--bg-card)] transition-colors"
|
||||||
|
>
|
||||||
|
<img
|
||||||
|
src={getImageUrl(img.url)}
|
||||||
|
alt=""
|
||||||
|
className="w-8 h-8 rounded object-cover border border-[var(--border)] flex-shrink-0"
|
||||||
|
/>
|
||||||
|
<div className="flex-1 min-w-0">
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)]">图片</div>
|
||||||
|
<div className="text-xs truncate">{img.prompt.slice(0, 30) || "（无 prompt）"}</div>
|
||||||
|
</div>
|
||||||
|
<Link
|
||||||
|
href="/gallery"
|
||||||
|
className="text-[10px] text-[var(--accent)] hover:underline flex-shrink-0"
|
||||||
|
>
|
||||||
|
↗
|
||||||
|
</Link>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
if (char) {
|
||||||
|
return (
|
||||||
|
<Link
|
||||||
|
key={key}
|
||||||
|
href={`/characters/${char.id}`}
|
||||||
|
className="mx-2 my-1 p-1.5 flex items-center gap-2 rounded-md
|
||||||
|
border border-[var(--border)] hover:border-[var(--accent)]/40
|
||||||
|
bg-[var(--bg-card)] transition-colors"
|
||||||
|
>
|
||||||
|
<div className="w-8 h-8 rounded-full bg-[var(--accent)]/10 border border-[var(--border)]
|
||||||
|
flex items-center justify-center text-[var(--accent)] text-xs font-semibold flex-shrink-0">
|
||||||
|
{char.name.charAt(0)}
|
||||||
|
</div>
|
||||||
|
<div className="flex-1 min-w-0">
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)]">角色</div>
|
||||||
|
<div className="text-xs truncate">{char.name}</div>
|
||||||
|
</div>
|
||||||
|
<span className="text-[10px] text-[var(--accent)] flex-shrink-0">↗</span>
|
||||||
|
</Link>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
if (style) {
|
||||||
|
return (
|
||||||
|
<Link
|
||||||
|
key={key}
|
||||||
|
href={`/styles/${style.id}`}
|
||||||
|
className="mx-2 my-1 p-1.5 flex items-center gap-2 rounded-md
|
||||||
|
border border-[var(--border)] hover:border-[var(--accent)]/40
|
||||||
|
bg-[var(--bg-card)] transition-colors"
|
||||||
|
>
|
||||||
|
<div className="w-8 h-8 rounded-md bg-gradient-to-br from-[var(--accent)] to-[var(--accent-secondary)]
|
||||||
|
opacity-60 flex-shrink-0" />
|
||||||
|
<div className="flex-1 min-w-0">
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)]">风格</div>
|
||||||
|
<div className="text-xs truncate">{style.name}</div>
|
||||||
|
</div>
|
||||||
|
<span className="text-[10px] text-[var(--accent-secondary)] flex-shrink-0">↗</span>
|
||||||
|
</Link>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
return (
|
||||||
|
<div key={key} className="mx-2 my-1 px-2 py-1 rounded-md text-[10px] font-mono
|
||||||
|
text-[var(--hot)]/70 bg-[var(--hot)]/5 border border-[var(--hot)]/20">
|
||||||
|
[[asset:{id}]] （未找到）
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
})
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* AI 助手占位 */}
|
||||||
|
<div className="flex-shrink-0 border-t border-[var(--border)] p-3">
|
||||||
|
<button
|
||||||
|
onClick={() => alert("AI 写作助手将在 Phase 2 接入：\n- 改写 / 扩写 / 概括 / 翻译\n- 基于项目上下文的续写\n- 从选中角色生成立绘 Prompt")}
|
||||||
|
className="w-full flex items-center justify-center gap-2 px-3 py-2 rounded-md
|
||||||
|
border border-dashed border-[var(--border)] bg-[var(--accent)]/5
|
||||||
|
text-xs text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:border-[var(--accent)]/40 cursor-pointer transition-all"
|
||||||
|
title="Phase 2 规划"
|
||||||
|
>
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M21 15a2 2 0 01-2 2H7l-4 4V5a2 2 0 012-2h14a2 2 0 012 2z" />
|
||||||
|
</svg>
|
||||||
|
AI 写作助手
|
||||||
|
<span className="phase-chip">P2</span>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
87
art-agent/frontend/src/components/docs/doc-tabs.tsx
Normal file
87
art-agent/frontend/src/components/docs/doc-tabs.tsx
Normal file
@@ -0,0 +1,87 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import type { DocNode } from "@/lib/types";
|
||||||
|
|
||||||
|
interface DocTabsProps {
|
||||||
|
openTabs: Array<{ node: DocNode; dirty: boolean }>;
|
||||||
|
activeId: string | null;
|
||||||
|
onActivate: (id: string) => void;
|
||||||
|
onClose: (id: string) => void;
|
||||||
|
onCloseOthers: (id: string) => void;
|
||||||
|
onCloseAll: () => void;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function DocTabs({
|
||||||
|
openTabs,
|
||||||
|
activeId,
|
||||||
|
onActivate,
|
||||||
|
onClose,
|
||||||
|
onCloseOthers,
|
||||||
|
onCloseAll,
|
||||||
|
}: DocTabsProps) {
|
||||||
|
if (openTabs.length === 0) return null;
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="flex-shrink-0 flex items-center border-b border-[var(--border)]
|
||||||
|
bg-[var(--bg-secondary)]/60 backdrop-blur-sm overflow-x-auto hide-scrollbar">
|
||||||
|
{openTabs.map((t) => {
|
||||||
|
const active = t.node.id === activeId;
|
||||||
|
return (
|
||||||
|
<div
|
||||||
|
key={t.node.id}
|
||||||
|
className={`flex items-center gap-1.5 pl-3 pr-2 py-1.5 cursor-pointer
|
||||||
|
border-r border-[var(--border)] min-w-0 max-w-[200px]
|
||||||
|
transition-all group flex-shrink-0 ${
|
||||||
|
active
|
||||||
|
? "bg-[var(--bg-primary)] text-[var(--accent)] border-t-2 border-t-[var(--accent)]"
|
||||||
|
: "text-[var(--text-secondary)] hover:text-[var(--text-primary)] hover:bg-[var(--accent)]/5 border-t-2 border-t-transparent"
|
||||||
|
}`}
|
||||||
|
onClick={() => onActivate(t.node.id)}
|
||||||
|
onMouseDown={(e) => {
|
||||||
|
if (e.button === 1) {
|
||||||
|
e.preventDefault();
|
||||||
|
onClose(t.node.id);
|
||||||
|
}
|
||||||
|
}}
|
||||||
|
onContextMenu={(e) => {
|
||||||
|
e.preventDefault();
|
||||||
|
const action = window.prompt(
|
||||||
|
`"${t.node.name}"：\n1=关闭此 Tab，2=关闭其他，3=关闭全部`,
|
||||||
|
"1"
|
||||||
|
);
|
||||||
|
if (action === "1") onClose(t.node.id);
|
||||||
|
else if (action === "2") onCloseOthers(t.node.id);
|
||||||
|
else if (action === "3") onCloseAll();
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" className="opacity-60 flex-shrink-0">
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
</svg>
|
||||||
|
<span className="text-xs truncate flex-1">{t.node.name}</span>
|
||||||
|
{t.dirty && !active && (
|
||||||
|
<span className="w-1.5 h-1.5 rounded-full bg-[var(--accent)]/60 flex-shrink-0" title="未保存" />
|
||||||
|
)}
|
||||||
|
{t.dirty && active && (
|
||||||
|
<span className="w-1.5 h-1.5 rounded-full bg-[var(--accent)] flex-shrink-0" title="未保存" />
|
||||||
|
)}
|
||||||
|
<button
|
||||||
|
onClick={(e) => {
|
||||||
|
e.stopPropagation();
|
||||||
|
onClose(t.node.id);
|
||||||
|
}}
|
||||||
|
className="w-4 h-4 rounded hover:bg-[var(--bg-tertiary)] text-[var(--text-secondary)]
|
||||||
|
hover:text-[var(--hot)] flex items-center justify-center flex-shrink-0
|
||||||
|
opacity-0 group-hover:opacity-100 transition-opacity"
|
||||||
|
title="关闭 Tab（中键）"
|
||||||
|
>
|
||||||
|
<svg width="9" height="9" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<path d="M18 6L6 18M6 6l12 12" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
})}
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
464
art-agent/frontend/src/components/docs/doc-tree.tsx
Normal file
464
art-agent/frontend/src/components/docs/doc-tree.tsx
Normal file
@@ -0,0 +1,464 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useState, useMemo, useRef, useEffect } from "react";
|
||||||
|
import type { DocNode } from "@/lib/types";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
|
||||||
|
interface DocTreeProps {
|
||||||
|
/** 当前选中的文档 ID（用于高亮） */
|
||||||
|
activeId: string | null;
|
||||||
|
/** 当前打开的文档 ID 集合（显示 • 标识） */
|
||||||
|
openIds: Set<string>;
|
||||||
|
onOpen: (node: DocNode) => void;
|
||||||
|
onSearch: (query: string) => void;
|
||||||
|
searchQuery: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function DocTree({ activeId, openIds, onOpen, onSearch, searchQuery }: DocTreeProps) {
|
||||||
|
const { docs, createDoc, renameDoc, deleteDoc, moveDoc } = useApp();
|
||||||
|
const [expanded, setExpanded] = useState<Set<string>>(
|
||||||
|
() => new Set(docs.filter((d) => d.type === "folder").map((d) => d.id))
|
||||||
|
);
|
||||||
|
const [contextMenu, setContextMenu] = useState<{ x: number; y: number; node: DocNode } | null>(null);
|
||||||
|
const [renamingId, setRenamingId] = useState<string | null>(null);
|
||||||
|
const [renameBuffer, setRenameBuffer] = useState("");
|
||||||
|
const [newNodeParent, setNewNodeParent] = useState<{ parentId: string | null; type: "folder" | "doc" } | null>(null);
|
||||||
|
const [newNodeName, setNewNodeName] = useState("");
|
||||||
|
const [dragOverId, setDragOverId] = useState<string | null>(null);
|
||||||
|
const renameInputRef = useRef<HTMLInputElement>(null);
|
||||||
|
const newNodeInputRef = useRef<HTMLInputElement>(null);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
if (renamingId && renameInputRef.current) {
|
||||||
|
renameInputRef.current.focus();
|
||||||
|
renameInputRef.current.select();
|
||||||
|
}
|
||||||
|
}, [renamingId]);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
if (newNodeParent && newNodeInputRef.current) {
|
||||||
|
newNodeInputRef.current.focus();
|
||||||
|
}
|
||||||
|
}, [newNodeParent]);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
if (!contextMenu) return;
|
||||||
|
const handler = () => setContextMenu(null);
|
||||||
|
window.addEventListener("click", handler);
|
||||||
|
window.addEventListener("blur", handler);
|
||||||
|
return () => {
|
||||||
|
window.removeEventListener("click", handler);
|
||||||
|
window.removeEventListener("blur", handler);
|
||||||
|
};
|
||||||
|
}, [contextMenu]);
|
||||||
|
|
||||||
|
const toggleExpand = (id: string) => {
|
||||||
|
setExpanded((prev) => {
|
||||||
|
const next = new Set(prev);
|
||||||
|
if (next.has(id)) next.delete(id);
|
||||||
|
else next.add(id);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
};
|
||||||
|
|
||||||
|
const filtered = useMemo(() => {
|
||||||
|
if (!searchQuery.trim()) return docs;
|
||||||
|
const q = searchQuery.toLowerCase();
|
||||||
|
const matches = (node: DocNode): boolean => {
|
||||||
|
if (node.name.toLowerCase().includes(q)) return true;
|
||||||
|
if (node.type === "doc" && (node.content ?? "").toLowerCase().includes(q)) return true;
|
||||||
|
if (node.children) return node.children.some(matches);
|
||||||
|
return false;
|
||||||
|
};
|
||||||
|
const filter = (list: DocNode[]): DocNode[] => {
|
||||||
|
return list
|
||||||
|
.map((n) => {
|
||||||
|
if (n.type === "folder") {
|
||||||
|
const kids = filter(n.children ?? []);
|
||||||
|
if (kids.length > 0 || n.name.toLowerCase().includes(q)) {
|
||||||
|
return { ...n, children: kids };
|
||||||
|
}
|
||||||
|
return null;
|
||||||
|
}
|
||||||
|
return matches(n) ? n : null;
|
||||||
|
})
|
||||||
|
.filter(Boolean) as DocNode[];
|
||||||
|
};
|
||||||
|
return filter(docs);
|
||||||
|
}, [docs, searchQuery]);
|
||||||
|
|
||||||
|
const startRename = (node: DocNode) => {
|
||||||
|
setContextMenu(null);
|
||||||
|
setRenamingId(node.id);
|
||||||
|
setRenameBuffer(node.name);
|
||||||
|
};
|
||||||
|
|
||||||
|
const commitRename = () => {
|
||||||
|
if (renamingId && renameBuffer.trim()) {
|
||||||
|
renameDoc(renamingId, renameBuffer.trim());
|
||||||
|
}
|
||||||
|
setRenamingId(null);
|
||||||
|
setRenameBuffer("");
|
||||||
|
};
|
||||||
|
|
||||||
|
const startNewNode = (parentId: string | null, type: "folder" | "doc") => {
|
||||||
|
setContextMenu(null);
|
||||||
|
if (parentId) setExpanded((prev) => new Set(prev).add(parentId));
|
||||||
|
setNewNodeParent({ parentId, type });
|
||||||
|
setNewNodeName(type === "folder" ? "新文件夹" : "新文档.md");
|
||||||
|
};
|
||||||
|
|
||||||
|
const commitNewNode = () => {
|
||||||
|
if (newNodeParent && newNodeName.trim()) {
|
||||||
|
const created = createDoc(newNodeParent.parentId, newNodeParent.type, newNodeName.trim());
|
||||||
|
if (created.type === "doc") onOpen(created);
|
||||||
|
}
|
||||||
|
setNewNodeParent(null);
|
||||||
|
setNewNodeName("");
|
||||||
|
};
|
||||||
|
|
||||||
|
const renderNode = (node: DocNode, depth: number) => {
|
||||||
|
const isFolder = node.type === "folder";
|
||||||
|
const isExpanded = expanded.has(node.id);
|
||||||
|
const isActive = activeId === node.id;
|
||||||
|
const isOpen = openIds.has(node.id);
|
||||||
|
const isRenaming = renamingId === node.id;
|
||||||
|
const isDragOver = dragOverId === node.id;
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div key={node.id}>
|
||||||
|
<div
|
||||||
|
draggable={!isRenaming}
|
||||||
|
onDragStart={(e) => {
|
||||||
|
e.dataTransfer.setData("application/x-docnode-id", node.id);
|
||||||
|
e.dataTransfer.effectAllowed = "move";
|
||||||
|
}}
|
||||||
|
onDragOver={(e) => {
|
||||||
|
if (isFolder) {
|
||||||
|
e.preventDefault();
|
||||||
|
e.dataTransfer.dropEffect = "move";
|
||||||
|
setDragOverId(node.id);
|
||||||
|
}
|
||||||
|
}}
|
||||||
|
onDragLeave={() => {
|
||||||
|
if (dragOverId === node.id) setDragOverId(null);
|
||||||
|
}}
|
||||||
|
onDrop={(e) => {
|
||||||
|
e.preventDefault();
|
||||||
|
setDragOverId(null);
|
||||||
|
if (!isFolder) return;
|
||||||
|
const draggedId = e.dataTransfer.getData("application/x-docnode-id");
|
||||||
|
if (draggedId && draggedId !== node.id) {
|
||||||
|
moveDoc(draggedId, node.id);
|
||||||
|
}
|
||||||
|
}}
|
||||||
|
className={`group flex items-center gap-1 pr-1 py-1 rounded-md cursor-pointer
|
||||||
|
${isActive ? "bg-[var(--accent)]/10 text-[var(--accent)]"
|
||||||
|
: "hover:bg-[var(--accent)]/5 text-[var(--text-primary)]"}
|
||||||
|
${isDragOver ? "ring-1 ring-[var(--accent)]/50 bg-[var(--accent)]/8" : ""}
|
||||||
|
transition-colors`}
|
||||||
|
style={{ paddingLeft: 6 + depth * 12 }}
|
||||||
|
onClick={() => {
|
||||||
|
if (isRenaming) return;
|
||||||
|
if (isFolder) toggleExpand(node.id);
|
||||||
|
else onOpen(node);
|
||||||
|
}}
|
||||||
|
onContextMenu={(e) => {
|
||||||
|
e.preventDefault();
|
||||||
|
setContextMenu({ x: e.clientX, y: e.clientY, node });
|
||||||
|
}}
|
||||||
|
onDoubleClick={(e) => {
|
||||||
|
e.stopPropagation();
|
||||||
|
if (!isRenaming) startRename(node);
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{isFolder ? (
|
||||||
|
<svg
|
||||||
|
width="10"
|
||||||
|
height="10"
|
||||||
|
viewBox="0 0 24 24"
|
||||||
|
fill="none"
|
||||||
|
stroke="currentColor"
|
||||||
|
strokeWidth="2.5"
|
||||||
|
className={`flex-shrink-0 transition-transform ${isExpanded ? "rotate-90" : ""}`}
|
||||||
|
>
|
||||||
|
<polyline points="9 18 15 12 9 6" />
|
||||||
|
</svg>
|
||||||
|
) : (
|
||||||
|
<span className="w-[10px]" />
|
||||||
|
)}
|
||||||
|
|
||||||
|
{isFolder ? (
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" className="flex-shrink-0 opacity-70">
|
||||||
|
<path d="M22 19a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h5l2 3h9a2 2 0 0 1 2 2z" />
|
||||||
|
</svg>
|
||||||
|
) : (
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" className="flex-shrink-0 opacity-60">
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
</svg>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{isRenaming ? (
|
||||||
|
<input
|
||||||
|
ref={renameInputRef}
|
||||||
|
value={renameBuffer}
|
||||||
|
onChange={(e) => setRenameBuffer(e.target.value)}
|
||||||
|
onBlur={commitRename}
|
||||||
|
onKeyDown={(e) => {
|
||||||
|
if (e.key === "Enter") commitRename();
|
||||||
|
if (e.key === "Escape") {
|
||||||
|
setRenamingId(null);
|
||||||
|
setRenameBuffer("");
|
||||||
|
}
|
||||||
|
}}
|
||||||
|
onClick={(e) => e.stopPropagation()}
|
||||||
|
className="flex-1 text-xs px-1 py-0 bg-[var(--bg-primary)] border border-[var(--accent)]/40
|
||||||
|
rounded outline-none focus:border-[var(--accent)]"
|
||||||
|
/>
|
||||||
|
) : (
|
||||||
|
<span className="text-xs truncate flex-1">{node.name}</span>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{isOpen && !isActive && (
|
||||||
|
<span className="w-1.5 h-1.5 rounded-full bg-[var(--accent)]/40 flex-shrink-0" title="已打开" />
|
||||||
|
)}
|
||||||
|
|
||||||
|
{isFolder && !isRenaming && (
|
||||||
|
<button
|
||||||
|
onClick={(e) => {
|
||||||
|
e.stopPropagation();
|
||||||
|
startNewNode(node.id, "doc");
|
||||||
|
}}
|
||||||
|
className="opacity-0 group-hover:opacity-100 text-[var(--text-secondary)]
|
||||||
|
hover:text-[var(--accent)] transition-opacity flex-shrink-0"
|
||||||
|
title="新建文档到此文件夹"
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<line x1="12" y1="5" x2="12" y2="19" />
|
||||||
|
<line x1="5" y1="12" x2="19" y2="12" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 新节点输入 */}
|
||||||
|
{newNodeParent && newNodeParent.parentId === node.id && isFolder && (
|
||||||
|
<div
|
||||||
|
className="flex items-center gap-1 py-1 rounded-md bg-[var(--accent)]/5"
|
||||||
|
style={{ paddingLeft: 6 + (depth + 1) * 12 }}
|
||||||
|
>
|
||||||
|
<span className="w-[10px]" />
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" className="flex-shrink-0 opacity-60">
|
||||||
|
{newNodeParent.type === "folder" ? (
|
||||||
|
<path d="M22 19a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h5l2 3h9a2 2 0 0 1 2 2z" />
|
||||||
|
) : (
|
||||||
|
<>
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
</svg>
|
||||||
|
<input
|
||||||
|
ref={newNodeInputRef}
|
||||||
|
value={newNodeName}
|
||||||
|
onChange={(e) => setNewNodeName(e.target.value)}
|
||||||
|
onBlur={commitNewNode}
|
||||||
|
onKeyDown={(e) => {
|
||||||
|
if (e.key === "Enter") commitNewNode();
|
||||||
|
if (e.key === "Escape") {
|
||||||
|
setNewNodeParent(null);
|
||||||
|
setNewNodeName("");
|
||||||
|
}
|
||||||
|
}}
|
||||||
|
className="flex-1 text-xs px-1 py-0 bg-[var(--bg-primary)] border border-[var(--accent)]/40
|
||||||
|
rounded outline-none focus:border-[var(--accent)] mr-1"
|
||||||
|
/>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{/* 子节点 */}
|
||||||
|
{isFolder && isExpanded && node.children && node.children.length > 0 && (
|
||||||
|
<div>{node.children.map((c) => renderNode(c, depth + 1))}</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
};
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="h-full flex flex-col">
|
||||||
|
{/* 头部 + 新建 */}
|
||||||
|
<div className="flex-shrink-0 px-3 pt-3 pb-2 flex items-center gap-2 border-b border-[var(--border)]">
|
||||||
|
<span className="typo-strong text-xs flex-1">文档</span>
|
||||||
|
<button
|
||||||
|
onClick={() => startNewNode(null, "doc")}
|
||||||
|
className="p-1 rounded-md text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:bg-[var(--accent)]/5 cursor-pointer transition-colors"
|
||||||
|
title="新建文档"
|
||||||
|
>
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
<line x1="12" y1="13" x2="12" y2="17" />
|
||||||
|
<line x1="10" y1="15" x2="14" y2="15" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
<button
|
||||||
|
onClick={() => startNewNode(null, "folder")}
|
||||||
|
className="p-1 rounded-md text-[var(--text-secondary)] hover:text-[var(--accent)]
|
||||||
|
hover:bg-[var(--accent)]/5 cursor-pointer transition-colors"
|
||||||
|
title="新建文件夹"
|
||||||
|
>
|
||||||
|
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M22 19a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h5l2 3h9a2 2 0 0 1 2 2z" />
|
||||||
|
<line x1="12" y1="11" x2="12" y2="17" />
|
||||||
|
<line x1="9" y1="14" x2="15" y2="14" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 搜索 */}
|
||||||
|
<div className="flex-shrink-0 px-3 py-2 border-b border-[var(--border)]">
|
||||||
|
<div className="flex items-center gap-1.5 px-2 py-1 rounded-md bg-[var(--bg-primary)]
|
||||||
|
border border-[var(--border)] focus-within:border-[var(--accent)]/40 transition-colors">
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="var(--text-secondary)" strokeWidth="2">
|
||||||
|
<circle cx="11" cy="11" r="8" />
|
||||||
|
<path d="M21 21l-4.35-4.35" />
|
||||||
|
</svg>
|
||||||
|
<input
|
||||||
|
value={searchQuery}
|
||||||
|
onChange={(e) => onSearch(e.target.value)}
|
||||||
|
placeholder="搜索文档（名称/内容）"
|
||||||
|
className="flex-1 text-xs bg-transparent border-none outline-none
|
||||||
|
text-[var(--text-primary)] placeholder:text-[var(--text-secondary)]/60"
|
||||||
|
/>
|
||||||
|
{searchQuery && (
|
||||||
|
<button
|
||||||
|
onClick={() => onSearch("")}
|
||||||
|
className="text-[var(--text-secondary)] hover:text-[var(--hot)] cursor-pointer"
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<path d="M18 6L6 18M6 6l12 12" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 树 */}
|
||||||
|
<div
|
||||||
|
className="flex-1 overflow-y-auto py-1"
|
||||||
|
onDragOver={(e) => {
|
||||||
|
e.preventDefault();
|
||||||
|
e.dataTransfer.dropEffect = "move";
|
||||||
|
}}
|
||||||
|
onDrop={(e) => {
|
||||||
|
e.preventDefault();
|
||||||
|
const draggedId = e.dataTransfer.getData("application/x-docnode-id");
|
||||||
|
if (draggedId) moveDoc(draggedId, null);
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{/* 根级新节点输入 */}
|
||||||
|
{newNodeParent && newNodeParent.parentId === null && (
|
||||||
|
<div className="flex items-center gap-1 py-1 rounded-md bg-[var(--accent)]/5 mx-1"
|
||||||
|
style={{ paddingLeft: 6 }}>
|
||||||
|
<span className="w-[10px]" />
|
||||||
|
<svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" className="flex-shrink-0 opacity-60">
|
||||||
|
{newNodeParent.type === "folder" ? (
|
||||||
|
<path d="M22 19a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h5l2 3h9a2 2 0 0 1 2 2z" />
|
||||||
|
) : (
|
||||||
|
<>
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
</svg>
|
||||||
|
<input
|
||||||
|
ref={newNodeInputRef}
|
||||||
|
value={newNodeName}
|
||||||
|
onChange={(e) => setNewNodeName(e.target.value)}
|
||||||
|
onBlur={commitNewNode}
|
||||||
|
onKeyDown={(e) => {
|
||||||
|
if (e.key === "Enter") commitNewNode();
|
||||||
|
if (e.key === "Escape") {
|
||||||
|
setNewNodeParent(null);
|
||||||
|
setNewNodeName("");
|
||||||
|
}
|
||||||
|
}}
|
||||||
|
className="flex-1 text-xs px-1 py-0 bg-[var(--bg-primary)] border border-[var(--accent)]/40
|
||||||
|
rounded outline-none focus:border-[var(--accent)] mr-1"
|
||||||
|
/>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{filtered.length === 0 ? (
|
||||||
|
<div className="px-3 py-8 text-center text-xs text-[var(--text-secondary)]">
|
||||||
|
{searchQuery ? "没有匹配的文档" : "还没有文档"}
|
||||||
|
</div>
|
||||||
|
) : (
|
||||||
|
<div className="px-1">{filtered.map((n) => renderNode(n, 0))}</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 右键菜单 */}
|
||||||
|
{contextMenu && (
|
||||||
|
<div
|
||||||
|
className="fixed z-50 rounded-lg surface-3 py-1 min-w-[160px] shadow-xl"
|
||||||
|
style={{ left: contextMenu.x, top: contextMenu.y }}
|
||||||
|
onClick={(e) => e.stopPropagation()}
|
||||||
|
>
|
||||||
|
{contextMenu.node.type === "folder" && (
|
||||||
|
<>
|
||||||
|
<ContextItem onClick={() => startNewNode(contextMenu.node.id, "doc")}>
|
||||||
|
新建文档
|
||||||
|
</ContextItem>
|
||||||
|
<ContextItem onClick={() => startNewNode(contextMenu.node.id, "folder")}>
|
||||||
|
新建文件夹
|
||||||
|
</ContextItem>
|
||||||
|
<Sep />
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
<ContextItem onClick={() => startRename(contextMenu.node)}>重命名</ContextItem>
|
||||||
|
<ContextItem
|
||||||
|
danger
|
||||||
|
onClick={() => {
|
||||||
|
if (confirm(`确定删除"${contextMenu.node.name}"？`)) {
|
||||||
|
deleteDoc(contextMenu.node.id);
|
||||||
|
}
|
||||||
|
setContextMenu(null);
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
删除
|
||||||
|
</ContextItem>
|
||||||
|
</div>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function ContextItem({
|
||||||
|
children,
|
||||||
|
onClick,
|
||||||
|
danger,
|
||||||
|
}: {
|
||||||
|
children: React.ReactNode;
|
||||||
|
onClick: () => void;
|
||||||
|
danger?: boolean;
|
||||||
|
}) {
|
||||||
|
return (
|
||||||
|
<button
|
||||||
|
onClick={onClick}
|
||||||
|
className={`w-full text-left px-3 py-1.5 text-xs cursor-pointer transition-colors ${
|
||||||
|
danger
|
||||||
|
? "text-[var(--hot)]/70 hover:text-[var(--hot)] hover:bg-[var(--hot)]/5"
|
||||||
|
: "text-[var(--text-primary)] hover:bg-[var(--accent)]/5 hover:text-[var(--accent)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{children}
|
||||||
|
</button>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function Sep() {
|
||||||
|
return <div className="border-t border-[var(--border)] my-1 mx-2" />;
|
||||||
|
}
|
||||||
240
art-agent/frontend/src/components/docs/markdown-content.tsx
Normal file
240
art-agent/frontend/src/components/docs/markdown-content.tsx
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useMemo } from "react";
|
||||||
|
import ReactMarkdown from "react-markdown";
|
||||||
|
import remarkGfm from "remark-gfm";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import { getImageUrl } from "@/lib/api";
|
||||||
|
import type { ImageAsset, CharacterCard, StylePack } from "@/lib/types";
|
||||||
|
|
||||||
|
interface MarkdownContentProps {
|
||||||
|
content: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 统一的 Markdown 渲染组件。
|
||||||
|
*
|
||||||
|
* 扩展语法：`[[asset:<id>]]` 会被替换为对应的资产卡片（图片/角色/风格）。
|
||||||
|
* 无法解析的引用会降级为纯文本。
|
||||||
|
*/
|
||||||
|
export function MarkdownContent({ content }: MarkdownContentProps) {
|
||||||
|
const { assets, characters, stylePacks } = useApp();
|
||||||
|
|
||||||
|
// 将 [[asset:xxx]] 替换为特殊占位符，渲染后再替换为 React 组件
|
||||||
|
const { processed, assetBlocks } = useMemo(() => {
|
||||||
|
const blocks: Array<{ placeholder: string; node: React.ReactNode }> = [];
|
||||||
|
let idx = 0;
|
||||||
|
const processed = content.replace(/\[\[asset:([^\]]+)\]\]/g, (_, id) => {
|
||||||
|
const placeholder = `%%ASSET_BLOCK_${idx}%%`;
|
||||||
|
idx++;
|
||||||
|
const img = assets.find((a) => a.id === id);
|
||||||
|
const char = characters.find((c) => c.id === id);
|
||||||
|
const style = stylePacks.find((s) => s.id === id);
|
||||||
|
blocks.push({
|
||||||
|
placeholder,
|
||||||
|
node: renderAssetCard({ id, img, char, style }),
|
||||||
|
});
|
||||||
|
return `\n\n${placeholder}\n\n`;
|
||||||
|
});
|
||||||
|
return { processed, assetBlocks: blocks };
|
||||||
|
}, [content, assets, characters, stylePacks]);
|
||||||
|
|
||||||
|
// 递归替换文本节点中的占位符
|
||||||
|
const renderWithAssets = (text: string): React.ReactNode => {
|
||||||
|
if (assetBlocks.length === 0) return text;
|
||||||
|
const parts: React.ReactNode[] = [];
|
||||||
|
let rest = text;
|
||||||
|
let idx = 0;
|
||||||
|
while (rest.length > 0) {
|
||||||
|
let found: { block: (typeof assetBlocks)[number]; at: number } | null = null;
|
||||||
|
for (const block of assetBlocks) {
|
||||||
|
const at = rest.indexOf(block.placeholder);
|
||||||
|
if (at >= 0 && (!found || at < found.at)) found = { block, at };
|
||||||
|
}
|
||||||
|
if (!found) {
|
||||||
|
if (rest) parts.push(<span key={idx++}>{rest}</span>);
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
if (found.at > 0) parts.push(<span key={idx++}>{rest.slice(0, found.at)}</span>);
|
||||||
|
parts.push(<span key={idx++}>{found.block.node}</span>);
|
||||||
|
rest = rest.slice(found.at + found.block.placeholder.length);
|
||||||
|
}
|
||||||
|
return <>{parts}</>;
|
||||||
|
};
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="markdown-body prose prose-sm max-w-none
|
||||||
|
text-[var(--text-primary)] leading-relaxed">
|
||||||
|
<ReactMarkdown
|
||||||
|
remarkPlugins={[remarkGfm]}
|
||||||
|
components={{
|
||||||
|
p: ({ children }) => {
|
||||||
|
if (typeof children === "string" && children.includes("%%ASSET_BLOCK_")) {
|
||||||
|
return <div className="my-3">{renderWithAssets(children)}</div>;
|
||||||
|
}
|
||||||
|
if (Array.isArray(children) && children.some((c) => typeof c === "string" && c.includes("%%ASSET_BLOCK_"))) {
|
||||||
|
return (
|
||||||
|
<div className="my-3">
|
||||||
|
{children.map((c, i) =>
|
||||||
|
typeof c === "string" && c.includes("%%ASSET_BLOCK_") ? (
|
||||||
|
<span key={i}>{renderWithAssets(c)}</span>
|
||||||
|
) : (
|
||||||
|
<span key={i}>{c}</span>
|
||||||
|
)
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
return <p className="my-2.5 text-sm leading-[1.7]">{children}</p>;
|
||||||
|
},
|
||||||
|
h1: ({ children }) => (
|
||||||
|
<h1 className="text-xl font-bold mt-6 mb-3 pb-2 border-b border-[var(--border)]">
|
||||||
|
{children}
|
||||||
|
</h1>
|
||||||
|
),
|
||||||
|
h2: ({ children }) => (
|
||||||
|
<h2 className="typo-h2 mt-5 mb-2.5">{children}</h2>
|
||||||
|
),
|
||||||
|
h3: ({ children }) => (
|
||||||
|
<h3 className="text-sm font-semibold text-[var(--accent)] mt-4 mb-2">
|
||||||
|
{children}
|
||||||
|
</h3>
|
||||||
|
),
|
||||||
|
ul: ({ children }) => <ul className="my-2 ml-5 list-disc space-y-1">{children}</ul>,
|
||||||
|
ol: ({ children }) => <ol className="my-2 ml-5 list-decimal space-y-1">{children}</ol>,
|
||||||
|
li: ({ children }) => <li className="text-sm leading-[1.7]">{children}</li>,
|
||||||
|
blockquote: ({ children }) => (
|
||||||
|
<blockquote className="my-3 pl-3 border-l-2 border-[var(--accent)]/50
|
||||||
|
text-[var(--text-secondary)] italic">
|
||||||
|
{children}
|
||||||
|
</blockquote>
|
||||||
|
),
|
||||||
|
code: ({ className, children }) => {
|
||||||
|
const isBlock = className?.includes("language-");
|
||||||
|
if (isBlock) {
|
||||||
|
return (
|
||||||
|
<code className="block p-3 my-2 rounded-lg bg-[var(--bg-secondary)] border border-[var(--border)]
|
||||||
|
text-xs font-mono overflow-x-auto whitespace-pre text-[var(--text-primary)]">
|
||||||
|
{children}
|
||||||
|
</code>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
return (
|
||||||
|
<code className="px-1.5 py-0.5 rounded text-xs font-mono
|
||||||
|
bg-[var(--bg-tertiary)] text-[var(--accent)]
|
||||||
|
border border-[var(--border)]">
|
||||||
|
{children}
|
||||||
|
</code>
|
||||||
|
);
|
||||||
|
},
|
||||||
|
pre: ({ children }) => <>{children}</>,
|
||||||
|
a: ({ href, children }) => (
|
||||||
|
<a
|
||||||
|
href={href}
|
||||||
|
target="_blank"
|
||||||
|
rel="noopener noreferrer"
|
||||||
|
className="text-[var(--accent)] underline decoration-[var(--accent)]/40 hover:decoration-[var(--accent)]"
|
||||||
|
>
|
||||||
|
{children}
|
||||||
|
</a>
|
||||||
|
),
|
||||||
|
table: ({ children }) => (
|
||||||
|
<div className="my-3 overflow-x-auto">
|
||||||
|
<table className="w-full border-collapse text-xs">{children}</table>
|
||||||
|
</div>
|
||||||
|
),
|
||||||
|
th: ({ children }) => (
|
||||||
|
<th className="px-3 py-2 bg-[var(--bg-secondary)] border border-[var(--border)]
|
||||||
|
text-left font-semibold text-[var(--accent)]">
|
||||||
|
{children}
|
||||||
|
</th>
|
||||||
|
),
|
||||||
|
td: ({ children }) => (
|
||||||
|
<td className="px-3 py-2 border border-[var(--border)]">{children}</td>
|
||||||
|
),
|
||||||
|
hr: () => <hr className="my-4 border-[var(--border)]" />,
|
||||||
|
strong: ({ children }) => (
|
||||||
|
<strong className="font-semibold text-[var(--accent)]">{children}</strong>
|
||||||
|
),
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{processed}
|
||||||
|
</ReactMarkdown>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
function renderAssetCard({
|
||||||
|
id,
|
||||||
|
img,
|
||||||
|
char,
|
||||||
|
style,
|
||||||
|
}: {
|
||||||
|
id: string;
|
||||||
|
img?: ImageAsset;
|
||||||
|
char?: CharacterCard;
|
||||||
|
style?: StylePack;
|
||||||
|
}): React.ReactNode {
|
||||||
|
if (img) {
|
||||||
|
return (
|
||||||
|
<span className="not-prose inline-flex items-center gap-2 my-2 px-2.5 py-1.5 rounded-lg
|
||||||
|
border border-[var(--accent)]/20 bg-[var(--accent)]/5
|
||||||
|
text-xs max-w-full">
|
||||||
|
<img
|
||||||
|
src={getImageUrl(img.url)}
|
||||||
|
alt=""
|
||||||
|
className="w-10 h-10 rounded-md object-cover border border-[var(--border)] flex-shrink-0"
|
||||||
|
/>
|
||||||
|
<span className="flex flex-col min-w-0">
|
||||||
|
<span className="text-[var(--accent)] font-medium text-[10px]">图片资产</span>
|
||||||
|
<span className="truncate text-[var(--text-primary)]">
|
||||||
|
{img.prompt.slice(0, 40) || "（无 prompt）"}
|
||||||
|
</span>
|
||||||
|
</span>
|
||||||
|
</span>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
if (char) {
|
||||||
|
return (
|
||||||
|
<span className="not-prose inline-flex items-center gap-2 my-2 px-2.5 py-1.5 rounded-lg
|
||||||
|
border border-[var(--accent)]/25 bg-[var(--accent)]/5
|
||||||
|
text-xs max-w-full">
|
||||||
|
<span className="w-8 h-8 rounded-full bg-[var(--bg-tertiary)] border border-[var(--border)]
|
||||||
|
flex-shrink-0 flex items-center justify-center text-[var(--accent)] font-semibold">
|
||||||
|
{char.name.charAt(0)}
|
||||||
|
</span>
|
||||||
|
<span className="flex flex-col min-w-0">
|
||||||
|
<span className="text-[var(--accent)] font-medium text-[10px]">角色</span>
|
||||||
|
<span className="truncate text-[var(--text-primary)]">{char.name}</span>
|
||||||
|
<span className="truncate text-[10px] text-[var(--text-secondary)]">
|
||||||
|
{char.visualHooks.slice(0, 3).join(" · ")}
|
||||||
|
</span>
|
||||||
|
</span>
|
||||||
|
</span>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
if (style) {
|
||||||
|
return (
|
||||||
|
<span className="not-prose inline-flex items-center gap-2 my-2 px-2.5 py-1.5 rounded-lg
|
||||||
|
border border-[var(--accent-secondary)]/30 bg-[var(--accent-secondary)]/5
|
||||||
|
text-xs max-w-full">
|
||||||
|
<span className="w-8 h-8 rounded-md bg-gradient-to-br from-[var(--accent)] to-[var(--accent-secondary)]
|
||||||
|
opacity-60 flex-shrink-0" />
|
||||||
|
<span className="flex flex-col min-w-0">
|
||||||
|
<span className="text-[var(--accent-secondary)] font-medium text-[10px]">风格</span>
|
||||||
|
<span className="truncate text-[var(--text-primary)]">{style.name}</span>
|
||||||
|
<span className="truncate text-[10px] text-[var(--text-secondary)]">
|
||||||
|
{style.keywords.slice(0, 3).join(" · ")}
|
||||||
|
</span>
|
||||||
|
</span>
|
||||||
|
</span>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
return (
|
||||||
|
<span className="not-prose inline-block my-1 px-2 py-0.5 rounded
|
||||||
|
border border-[var(--hot)]/30 bg-[var(--hot)]/5
|
||||||
|
text-[10px] text-[var(--hot)] font-mono">
|
||||||
|
[[asset:{id}]] （未找到）
|
||||||
|
</span>
|
||||||
|
);
|
||||||
|
}
|
||||||
@@ -21,6 +21,19 @@ const NAV_ITEMS = [
|
|||||||
</svg>
|
</svg>
|
||||||
),
|
),
|
||||||
},
|
},
|
||||||
|
{
|
||||||
|
href: "/docs",
|
||||||
|
label: "文档",
|
||||||
|
phase: "Phase 1",
|
||||||
|
icon: (
|
||||||
|
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z" />
|
||||||
|
<polyline points="14 2 14 8 20 8" />
|
||||||
|
<line x1="8" y1="13" x2="16" y2="13" />
|
||||||
|
<line x1="8" y1="17" x2="13" y2="17" />
|
||||||
|
</svg>
|
||||||
|
),
|
||||||
|
},
|
||||||
{
|
{
|
||||||
href: "/gallery",
|
href: "/gallery",
|
||||||
label: "资源库",
|
label: "资源库",
|
||||||
|
|||||||
@@ -45,7 +45,7 @@ export const assistantEnter: Variants = {
|
|||||||
export const buttonTap = { scale: 0.85 };
|
export const buttonTap = { scale: 0.85 };
|
||||||
export const sendBounce = {
|
export const sendBounce = {
|
||||||
scale: [1, 0.85, 1.08, 1],
|
scale: [1, 0.85, 1.08, 1],
|
||||||
transition: { duration: 0.35, ease: "easeInOut" },
|
transition: { duration: 0.35, ease: "easeInOut" as const },
|
||||||
};
|
};
|
||||||
|
|
||||||
/* ===== 涟漪 ===== */
|
/* ===== 涟漪 ===== */
|
||||||
|
|||||||
138
art-agent/frontend/src/components/workbench/params-3d.tsx
Normal file
138
art-agent/frontend/src/components/workbench/params-3d.tsx
Normal file
@@ -0,0 +1,138 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useState } from "react";
|
||||||
|
import type { Params3D } from "@/lib/types";
|
||||||
|
|
||||||
|
const PIPELINE_OPTIONS: { id: Params3D["pipeline"]; label: string; desc: string }[] = [
|
||||||
|
{ id: "trellis", label: "Trellis", desc: "稳定细节，中速" },
|
||||||
|
{ id: "hunyuan3d", label: "Hunyuan 3D", desc: "适合复杂几何" },
|
||||||
|
{ id: "zero123plus", label: "Zero123++", desc: "快速低保真" },
|
||||||
|
];
|
||||||
|
|
||||||
|
const RESOLUTION_OPTIONS = ["512×512", "768×768", "1024×1024"];
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 3D 模型生成参数条（Phase 2 占位）
|
||||||
|
*
|
||||||
|
* 对应 Mesh Pipeline 的 Stage 1（多视图渲染）参数：
|
||||||
|
* - 管道选择（trellis / hunyuan3d / zero123plus）
|
||||||
|
* - 视图数（4 / 6 / 8 / 12）
|
||||||
|
* - 方位角预设（等距 / 自定义）
|
||||||
|
* - 是否保持原图风格（IP-Adapter 色彩还原）
|
||||||
|
* - 分辨率
|
||||||
|
*/
|
||||||
|
export function Params3D() {
|
||||||
|
const [pipeline, setPipeline] = useState<Params3D["pipeline"]>("trellis");
|
||||||
|
const [viewCount, setViewCount] = useState(6);
|
||||||
|
const [preserveStyle, setPreserveStyle] = useState(true);
|
||||||
|
const [resolution, setResolution] = useState("768×768");
|
||||||
|
const [pipelineOpen, setPipelineOpen] = useState(false);
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="relative px-3 md:px-5 py-1 flex items-center gap-1.5 flex-wrap
|
||||||
|
border-t border-[var(--border)]/40 bg-[var(--accent)]/[0.02]">
|
||||||
|
<span className="typo-micro text-[10px]" style={{ textTransform: "none" }}>
|
||||||
|
3D 参数
|
||||||
|
</span>
|
||||||
|
<span className="phase-chip">P2</span>
|
||||||
|
|
||||||
|
{/* 管道 */}
|
||||||
|
<div className="relative">
|
||||||
|
<button
|
||||||
|
onClick={() => setPipelineOpen(!pipelineOpen)}
|
||||||
|
className="h-6 px-2 rounded-md text-[11px] flex items-center gap-1
|
||||||
|
border border-[var(--border)] bg-[var(--bg-tertiary)]
|
||||||
|
text-[var(--text-secondary)] hover:text-[var(--text-primary)]
|
||||||
|
hover:border-[var(--accent)]/40 cursor-pointer transition-all"
|
||||||
|
title="生成管道"
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<path d="M12 2L2 7l10 5 10-5-10-5z" />
|
||||||
|
</svg>
|
||||||
|
{PIPELINE_OPTIONS.find((p) => p.id === pipeline)?.label}
|
||||||
|
<svg width="8" height="8" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<polyline points="6 9 12 15 18 9" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
{pipelineOpen && (
|
||||||
|
<>
|
||||||
|
<div className="fixed inset-0 z-30" onClick={() => setPipelineOpen(false)} />
|
||||||
|
<div className="absolute bottom-full mb-1 left-0 z-40 min-w-[200px]
|
||||||
|
surface-3 rounded-lg overflow-hidden shadow-xl">
|
||||||
|
{PIPELINE_OPTIONS.map((p) => (
|
||||||
|
<button
|
||||||
|
key={p.id}
|
||||||
|
onClick={() => {
|
||||||
|
setPipeline(p.id);
|
||||||
|
setPipelineOpen(false);
|
||||||
|
}}
|
||||||
|
className={`w-full px-3 py-2 text-left text-xs cursor-pointer transition-colors
|
||||||
|
${pipeline === p.id ? "bg-[var(--accent)]/10 text-[var(--accent)]" : "hover:bg-[var(--accent)]/5"}`}
|
||||||
|
>
|
||||||
|
<div className="font-medium">{p.label}</div>
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)]">{p.desc}</div>
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 视图数 */}
|
||||||
|
<div className="flex items-center gap-0.5 p-0.5 rounded-md bg-[var(--bg-tertiary)] border border-[var(--border)]">
|
||||||
|
<span className="px-1.5 text-[10px] text-[var(--text-secondary)]">视图</span>
|
||||||
|
{[4, 6, 8, 12].map((n) => (
|
||||||
|
<button
|
||||||
|
key={n}
|
||||||
|
onClick={() => setViewCount(n)}
|
||||||
|
className={`h-5 px-1.5 rounded text-[10px] cursor-pointer transition-all font-mono ${
|
||||||
|
viewCount === n
|
||||||
|
? "bg-[var(--accent)]/12 text-[var(--accent)]"
|
||||||
|
: "text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{n}
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 保持风格 */}
|
||||||
|
<button
|
||||||
|
onClick={() => setPreserveStyle(!preserveStyle)}
|
||||||
|
className={`h-6 px-2 rounded-md text-[11px] flex items-center gap-1 cursor-pointer transition-all ${
|
||||||
|
preserveStyle
|
||||||
|
? "border border-[var(--accent)]/30 bg-[var(--accent)]/8 text-[var(--accent)]"
|
||||||
|
: "border border-[var(--border)] bg-[var(--bg-tertiary)] text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
title="IP-Adapter 风格还原，保留原立绘色彩"
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill={preserveStyle ? "currentColor" : "none"} stroke="currentColor" strokeWidth="2">
|
||||||
|
<circle cx="13.5" cy="6.5" r="0.5" />
|
||||||
|
<circle cx="17.5" cy="10.5" r="0.5" />
|
||||||
|
<circle cx="8.5" cy="7.5" r="0.5" />
|
||||||
|
<circle cx="6.5" cy="12.5" r="0.5" />
|
||||||
|
<path d="M12 2C6.5 2 2 6.5 2 12s4.5 10 10 10c.8 0 1.5-.7 1.5-1.5 0-.4-.2-.8-.4-1.1-.2-.3-.4-.7-.4-1.1 0-.8.7-1.5 1.5-1.5H16c3.3 0 6-2.7 6-6 0-5-4.5-9-10-9z" />
|
||||||
|
</svg>
|
||||||
|
保持风格
|
||||||
|
</button>
|
||||||
|
|
||||||
|
{/* 分辨率 */}
|
||||||
|
<select
|
||||||
|
value={resolution}
|
||||||
|
onChange={(e) => setResolution(e.target.value)}
|
||||||
|
className="h-6 px-1.5 text-[11px] rounded-md bg-[var(--bg-tertiary)]
|
||||||
|
border border-[var(--border)] focus:border-[var(--accent)]/40 outline-none cursor-pointer"
|
||||||
|
>
|
||||||
|
{RESOLUTION_OPTIONS.map((r) => (
|
||||||
|
<option key={r} value={r}>
|
||||||
|
{r}
|
||||||
|
</option>
|
||||||
|
))}
|
||||||
|
</select>
|
||||||
|
|
||||||
|
<span className="ml-auto text-[10px] text-[var(--text-secondary)] hidden md:inline">
|
||||||
|
Mesh Pipeline · 多视图 → 法线 → 风格化 → GLB
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
200
art-agent/frontend/src/components/workbench/params-motion.tsx
Normal file
200
art-agent/frontend/src/components/workbench/params-motion.tsx
Normal file
@@ -0,0 +1,200 @@
|
|||||||
|
"use client";
|
||||||
|
|
||||||
|
import { useState } from "react";
|
||||||
|
import { useApp } from "@/lib/app-context";
|
||||||
|
import type { ParamsMotion } from "@/lib/types";
|
||||||
|
|
||||||
|
const MODEL_OPTIONS: { id: ParamsMotion["model"]; label: string; desc: string }[] = [
|
||||||
|
{ id: "animatediff", label: "AnimateDiff", desc: "动作幅度大" },
|
||||||
|
{ id: "svd", label: "Stable Video", desc: "物理动态佳" },
|
||||||
|
{ id: "motion-lora", label: "Motion LoRA", desc: "绑定角色 LoRA" },
|
||||||
|
];
|
||||||
|
|
||||||
|
const MOTION_PRESETS = [
|
||||||
|
"待机（idle）",
|
||||||
|
"行走（walk）",
|
||||||
|
"挥剑（slash）",
|
||||||
|
"跳跃（jump）",
|
||||||
|
"施法（cast）",
|
||||||
|
];
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 动作/动画生成参数条（Phase 2 占位）
|
||||||
|
*
|
||||||
|
* - 模型选择（animatediff / svd / motion-lora）
|
||||||
|
* - 帧数（8~32）
|
||||||
|
* - 帧率（8 / 12 / 24 fps）
|
||||||
|
* - 是否循环
|
||||||
|
* - 输出格式（mp4 / gif / frames）
|
||||||
|
* - 绑定角色
|
||||||
|
* - 动作描述关键词（自然语言或预设）
|
||||||
|
*/
|
||||||
|
export function ParamsMotionBar() {
|
||||||
|
const { characters } = useApp();
|
||||||
|
const [model, setModel] = useState<ParamsMotion["model"]>("animatediff");
|
||||||
|
const [frameCount, setFrameCount] = useState(16);
|
||||||
|
const [fps, setFps] = useState(12);
|
||||||
|
const [loop, setLoop] = useState(true);
|
||||||
|
const [output, setOutput] = useState<ParamsMotion["output"]>("mp4");
|
||||||
|
const [characterId, setCharacterId] = useState<string>("");
|
||||||
|
const [motionHint, setMotionHint] = useState<string>("");
|
||||||
|
const [modelOpen, setModelOpen] = useState(false);
|
||||||
|
|
||||||
|
const duration = (frameCount / fps).toFixed(2);
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="relative px-3 md:px-5 py-1 flex items-center gap-1.5 flex-wrap
|
||||||
|
border-t border-[var(--border)]/40 bg-[var(--accent-secondary)]/[0.03]">
|
||||||
|
<span className="typo-micro text-[10px]" style={{ textTransform: "none" }}>
|
||||||
|
动作参数
|
||||||
|
</span>
|
||||||
|
<span className="phase-chip">P2</span>
|
||||||
|
|
||||||
|
{/* 模型 */}
|
||||||
|
<div className="relative">
|
||||||
|
<button
|
||||||
|
onClick={() => setModelOpen(!modelOpen)}
|
||||||
|
className="h-6 px-2 rounded-md text-[11px] flex items-center gap-1
|
||||||
|
border border-[var(--border)] bg-[var(--bg-tertiary)]
|
||||||
|
text-[var(--text-secondary)] hover:text-[var(--text-primary)]
|
||||||
|
hover:border-[var(--accent)]/40 cursor-pointer transition-all"
|
||||||
|
title="动作生成模型"
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polygon points="5 3 19 12 5 21 5 3" />
|
||||||
|
</svg>
|
||||||
|
{MODEL_OPTIONS.find((m) => m.id === model)?.label}
|
||||||
|
<svg width="8" height="8" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5">
|
||||||
|
<polyline points="6 9 12 15 18 9" />
|
||||||
|
</svg>
|
||||||
|
</button>
|
||||||
|
{modelOpen && (
|
||||||
|
<>
|
||||||
|
<div className="fixed inset-0 z-30" onClick={() => setModelOpen(false)} />
|
||||||
|
<div className="absolute bottom-full mb-1 left-0 z-40 min-w-[200px]
|
||||||
|
surface-3 rounded-lg overflow-hidden shadow-xl">
|
||||||
|
{MODEL_OPTIONS.map((m) => (
|
||||||
|
<button
|
||||||
|
key={m.id}
|
||||||
|
onClick={() => {
|
||||||
|
setModel(m.id);
|
||||||
|
setModelOpen(false);
|
||||||
|
}}
|
||||||
|
className={`w-full px-3 py-2 text-left text-xs cursor-pointer transition-colors
|
||||||
|
${model === m.id ? "bg-[var(--accent)]/10 text-[var(--accent)]" : "hover:bg-[var(--accent)]/5"}`}
|
||||||
|
>
|
||||||
|
<div className="font-medium">{m.label}</div>
|
||||||
|
<div className="text-[10px] text-[var(--text-secondary)]">{m.desc}</div>
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
</>
|
||||||
|
)}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 帧数 */}
|
||||||
|
<label className="flex items-center gap-1 h-6 px-2 rounded-md bg-[var(--bg-tertiary)]
|
||||||
|
border border-[var(--border)] text-[11px]">
|
||||||
|
<span className="text-[var(--text-secondary)]">帧</span>
|
||||||
|
<input
|
||||||
|
type="number"
|
||||||
|
min={4}
|
||||||
|
max={64}
|
||||||
|
value={frameCount}
|
||||||
|
onChange={(e) => setFrameCount(Math.max(4, Math.min(64, parseInt(e.target.value) || 16)))}
|
||||||
|
className="w-10 bg-transparent border-none outline-none text-center font-mono text-[var(--text-primary)]"
|
||||||
|
/>
|
||||||
|
</label>
|
||||||
|
|
||||||
|
{/* 帧率 */}
|
||||||
|
<div className="flex items-center gap-0.5 p-0.5 rounded-md bg-[var(--bg-tertiary)] border border-[var(--border)]">
|
||||||
|
<span className="px-1.5 text-[10px] text-[var(--text-secondary)]">fps</span>
|
||||||
|
{[8, 12, 24].map((f) => (
|
||||||
|
<button
|
||||||
|
key={f}
|
||||||
|
onClick={() => setFps(f)}
|
||||||
|
className={`h-5 px-1.5 rounded text-[10px] cursor-pointer transition-all font-mono ${
|
||||||
|
fps === f
|
||||||
|
? "bg-[var(--accent)]/12 text-[var(--accent)]"
|
||||||
|
: "text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
>
|
||||||
|
{f}
|
||||||
|
</button>
|
||||||
|
))}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
{/* 时长显示 */}
|
||||||
|
<span className="text-[10px] text-[var(--text-secondary)] font-mono">
|
||||||
|
≈ {duration}s
|
||||||
|
</span>
|
||||||
|
|
||||||
|
{/* 循环 */}
|
||||||
|
<button
|
||||||
|
onClick={() => setLoop(!loop)}
|
||||||
|
className={`h-6 px-2 rounded-md text-[11px] flex items-center gap-1 cursor-pointer transition-all ${
|
||||||
|
loop
|
||||||
|
? "border border-[var(--accent)]/30 bg-[var(--accent)]/8 text-[var(--accent)]"
|
||||||
|
: "border border-[var(--border)] bg-[var(--bg-tertiary)] text-[var(--text-secondary)] hover:text-[var(--text-primary)]"
|
||||||
|
}`}
|
||||||
|
title="循环播放"
|
||||||
|
>
|
||||||
|
<svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||||
|
<polyline points="17 1 21 5 17 9" />
|
||||||
|
<path d="M3 11V9a4 4 0 0 1 4-4h14" />
|
||||||
|
<polyline points="7 23 3 19 7 15" />
|
||||||
|
<path d="M21 13v2a4 4 0 0 1-4 4H3" />
|
||||||
|
</svg>
|
||||||
|
循环
|
||||||
|
</button>
|
||||||
|
|
||||||
|
{/* 输出格式 */}
|
||||||
|
<select
|
||||||
|
value={output}
|
||||||
|
onChange={(e) => setOutput(e.target.value as ParamsMotion["output"])}
|
||||||
|
className="h-6 px-1.5 text-[11px] rounded-md bg-[var(--bg-tertiary)]
|
||||||
|
border border-[var(--border)] focus:border-[var(--accent)]/40 outline-none cursor-pointer font-mono"
|
||||||
|
>
|
||||||
|
<option value="mp4">MP4</option>
|
||||||
|
<option value="gif">GIF</option>
|
||||||
|
<option value="frames">帧序列</option>
|
||||||
|
</select>
|
||||||
|
|
||||||
|
{/* 绑定角色 */}
|
||||||
|
{characters.length > 0 && (
|
||||||
|
<select
|
||||||
|
value={characterId}
|
||||||
|
onChange={(e) => setCharacterId(e.target.value)}
|
||||||
|
className="h-6 px-1.5 text-[11px] rounded-md bg-[var(--bg-tertiary)]
|
||||||
|
border border-[var(--border)] focus:border-[var(--accent)]/40 outline-none cursor-pointer max-w-[120px]"
|
||||||
|
title="绑定角色（用于保持人物一致性）"
|
||||||
|
>
|
||||||
|
<option value="">无绑定角色</option>
|
||||||
|
{characters.map((c) => (
|
||||||
|
<option key={c.id} value={c.id}>
|
||||||
|
{c.name}
|
||||||
|
</option>
|
||||||
|
))}
|
||||||
|
</select>
|
||||||
|
)}
|
||||||
|
|
||||||
|
{/* 动作提示（自然语言） */}
|
||||||
|
<div className="flex items-center gap-1 flex-1 min-w-[140px] max-w-[240px]">
|
||||||
|
<input
|
||||||
|
list="motion-presets"
|
||||||
|
value={motionHint}
|
||||||
|
onChange={(e) => setMotionHint(e.target.value)}
|
||||||
|
placeholder="动作关键词（可选）"
|
||||||
|
className="flex-1 h-6 px-2 text-[11px] rounded-md bg-[var(--bg-tertiary)]
|
||||||
|
border border-[var(--border)] focus:border-[var(--accent)]/40 outline-none
|
||||||
|
text-[var(--text-primary)] placeholder:text-[var(--text-secondary)]"
|
||||||
|
/>
|
||||||
|
<datalist id="motion-presets">
|
||||||
|
{MOTION_PRESETS.map((p) => (
|
||||||
|
<option key={p} value={p} />
|
||||||
|
))}
|
||||||
|
</datalist>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
@@ -18,6 +18,10 @@ import type {
|
|||||||
StylePack,
|
StylePack,
|
||||||
CharacterCard,
|
CharacterCard,
|
||||||
TrainingTask,
|
TrainingTask,
|
||||||
|
DocNode,
|
||||||
|
Asset3D,
|
||||||
|
AssetMotion,
|
||||||
|
TaskType,
|
||||||
} from "./types";
|
} from "./types";
|
||||||
import {
|
import {
|
||||||
loadSessions,
|
loadSessions,
|
||||||
@@ -51,6 +55,14 @@ import {
|
|||||||
loadTrainingTasks,
|
loadTrainingTasks,
|
||||||
upsertTrainingTask as storeUpsertTraining,
|
upsertTrainingTask as storeUpsertTraining,
|
||||||
deleteTrainingTask as storeDeleteTraining,
|
deleteTrainingTask as storeDeleteTraining,
|
||||||
|
loadDocs,
|
||||||
|
saveDocs,
|
||||||
|
loadAssets3D,
|
||||||
|
upsertAsset3D as storeUpsertAsset3D,
|
||||||
|
deleteAsset3D as storeDeleteAsset3D,
|
||||||
|
loadAssetsMotion,
|
||||||
|
upsertAssetMotion as storeUpsertAssetMotion,
|
||||||
|
deleteAssetMotion as storeDeleteAssetMotion,
|
||||||
} from "./placeholder-store";
|
} from "./placeholder-store";
|
||||||
import { useAuth } from "./auth-context";
|
import { useAuth } from "./auth-context";
|
||||||
|
|
||||||
@@ -117,6 +129,32 @@ interface AppContextValue {
|
|||||||
/** 当前会话选择的资产规格（占位） */
|
/** 当前会话选择的资产规格（占位） */
|
||||||
sessionAssetSpec: string | null;
|
sessionAssetSpec: string | null;
|
||||||
setSessionAssetSpec: (spec: string | null) => void;
|
setSessionAssetSpec: (spec: string | null) => void;
|
||||||
|
|
||||||
|
// ===== 文档管理中心（Phase 1） =====
|
||||||
|
docs: DocNode[];
|
||||||
|
upsertDoc: (path: string[], node: DocNode) => void;
|
||||||
|
renameDoc: (nodeId: string, newName: string) => void;
|
||||||
|
deleteDoc: (nodeId: string) => void;
|
||||||
|
moveDoc: (nodeId: string, newParentId: string | null) => void;
|
||||||
|
updateDocContent: (nodeId: string, content: string) => void;
|
||||||
|
createDoc: (parentId: string | null, type: "folder" | "doc", name: string) => DocNode;
|
||||||
|
|
||||||
|
// ===== 3D / 动作资产（Phase 2） =====
|
||||||
|
assets3D: Asset3D[];
|
||||||
|
upsertAsset3D: (a: Asset3D) => void;
|
||||||
|
deleteAsset3D: (id: string) => void;
|
||||||
|
|
||||||
|
assetsMotion: AssetMotion[];
|
||||||
|
upsertAssetMotion: (a: AssetMotion) => void;
|
||||||
|
deleteAssetMotion: (id: string) => void;
|
||||||
|
|
||||||
|
// ===== 工作台任务类型（2D / 3D / 动作） =====
|
||||||
|
sessionTaskType: TaskType;
|
||||||
|
setSessionTaskType: (t: TaskType) => void;
|
||||||
|
|
||||||
|
// ===== 全站命令面板 =====
|
||||||
|
commandPaletteOpen: boolean;
|
||||||
|
setCommandPaletteOpen: (v: boolean) => void;
|
||||||
}
|
}
|
||||||
|
|
||||||
const AppContext = createContext<AppContextValue | null>(null);
|
const AppContext = createContext<AppContextValue | null>(null);
|
||||||
@@ -151,6 +189,11 @@ export function AppProvider({ children }: { children: ReactNode }) {
|
|||||||
const [sessionStyleId, setSessionStyleId] = useState<string | null>(null);
|
const [sessionStyleId, setSessionStyleId] = useState<string | null>(null);
|
||||||
const [sessionCharacterId, setSessionCharacterId] = useState<string | null>(null);
|
const [sessionCharacterId, setSessionCharacterId] = useState<string | null>(null);
|
||||||
const [sessionAssetSpec, setSessionAssetSpec] = useState<string | null>(null);
|
const [sessionAssetSpec, setSessionAssetSpec] = useState<string | null>(null);
|
||||||
|
const [docs, setDocs] = useState<DocNode[]>([]);
|
||||||
|
const [assets3D, setAssets3D] = useState<Asset3D[]>([]);
|
||||||
|
const [assetsMotion, setAssetsMotion] = useState<AssetMotion[]>([]);
|
||||||
|
const [sessionTaskType, setSessionTaskType] = useState<TaskType>("image2d");
|
||||||
|
const [commandPaletteOpen, setCommandPaletteOpen] = useState(false);
|
||||||
|
|
||||||
// 当用户变化时，切换 store 的 userId 并重新加载数据
|
// 当用户变化时，切换 store 的 userId 并重新加载数据
|
||||||
useEffect(() => {
|
useEffect(() => {
|
||||||
@@ -167,11 +210,15 @@ export function AppProvider({ children }: { children: ReactNode }) {
|
|||||||
setStylePacks(loadStylePacks());
|
setStylePacks(loadStylePacks());
|
||||||
setCharacters(loadCharacters());
|
setCharacters(loadCharacters());
|
||||||
setTrainingTasks(loadTrainingTasks());
|
setTrainingTasks(loadTrainingTasks());
|
||||||
|
setDocs(loadDocs());
|
||||||
|
setAssets3D(loadAssets3D());
|
||||||
|
setAssetsMotion(loadAssetsMotion());
|
||||||
setActiveSessionId(null);
|
setActiveSessionId(null);
|
||||||
setDetailImage(null);
|
setDetailImage(null);
|
||||||
setSessionStyleId(null);
|
setSessionStyleId(null);
|
||||||
setSessionCharacterId(null);
|
setSessionCharacterId(null);
|
||||||
setSessionAssetSpec(null);
|
setSessionAssetSpec(null);
|
||||||
|
setSessionTaskType("image2d");
|
||||||
setInitialized(true);
|
setInitialized(true);
|
||||||
}, [user?.id, isAuthenticated]); // eslint-disable-line react-hooks/exhaustive-deps
|
}, [user?.id, isAuthenticated]); // eslint-disable-line react-hooks/exhaustive-deps
|
||||||
|
|
||||||
@@ -393,6 +440,169 @@ export function AppProvider({ children }: { children: ReactNode }) {
|
|||||||
setTrainingTasks(loadTrainingTasks());
|
setTrainingTasks(loadTrainingTasks());
|
||||||
}, []);
|
}, []);
|
||||||
|
|
||||||
|
// ===== 文档操作（Phase 1，纯 localStorage 占位） =====
|
||||||
|
|
||||||
|
/** 在树中递归查找节点的父列表引用 */
|
||||||
|
const findNodeParentList = useCallback(
|
||||||
|
(tree: DocNode[], nodeId: string): { list: DocNode[]; idx: number } | null => {
|
||||||
|
for (let i = 0; i < tree.length; i++) {
|
||||||
|
if (tree[i].id === nodeId) return { list: tree, idx: i };
|
||||||
|
if (tree[i].children && tree[i].children!.length > 0) {
|
||||||
|
const r = findNodeParentList(tree[i].children!, nodeId);
|
||||||
|
if (r) return r;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return null;
|
||||||
|
},
|
||||||
|
[]
|
||||||
|
);
|
||||||
|
|
||||||
|
const createDoc = useCallback(
|
||||||
|
(parentId: string | null, type: "folder" | "doc", name: string): DocNode => {
|
||||||
|
const now = Date.now();
|
||||||
|
const node: DocNode = {
|
||||||
|
id: generateId(type === "folder" ? "doc-folder-" : "doc-"),
|
||||||
|
type,
|
||||||
|
name,
|
||||||
|
content: type === "doc" ? `# ${name.replace(/\.md$/, "")}\n\n` : undefined,
|
||||||
|
children: type === "folder" ? [] : undefined,
|
||||||
|
projectId: activeProjectId || undefined,
|
||||||
|
order: 0,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
};
|
||||||
|
setDocs((prev) => {
|
||||||
|
const next = structuredClone(prev) as DocNode[];
|
||||||
|
if (parentId === null) {
|
||||||
|
next.unshift(node);
|
||||||
|
} else {
|
||||||
|
const found = findNodeParentList(next, parentId);
|
||||||
|
if (found) {
|
||||||
|
const parent = found.list[found.idx];
|
||||||
|
if (parent.type === "folder") {
|
||||||
|
parent.children = parent.children ?? [];
|
||||||
|
parent.children.unshift(node);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
saveDocs(next);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
return node;
|
||||||
|
},
|
||||||
|
[activeProjectId, findNodeParentList]
|
||||||
|
);
|
||||||
|
|
||||||
|
const renameDoc = useCallback(
|
||||||
|
(nodeId: string, newName: string) => {
|
||||||
|
setDocs((prev) => {
|
||||||
|
const next = structuredClone(prev) as DocNode[];
|
||||||
|
const found = findNodeParentList(next, nodeId);
|
||||||
|
if (found) {
|
||||||
|
found.list[found.idx].name = newName;
|
||||||
|
found.list[found.idx].updatedAt = Date.now();
|
||||||
|
}
|
||||||
|
saveDocs(next);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
},
|
||||||
|
[findNodeParentList]
|
||||||
|
);
|
||||||
|
|
||||||
|
const deleteDoc = useCallback(
|
||||||
|
(nodeId: string) => {
|
||||||
|
setDocs((prev) => {
|
||||||
|
const next = structuredClone(prev) as DocNode[];
|
||||||
|
const found = findNodeParentList(next, nodeId);
|
||||||
|
if (found) found.list.splice(found.idx, 1);
|
||||||
|
saveDocs(next);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
},
|
||||||
|
[findNodeParentList]
|
||||||
|
);
|
||||||
|
|
||||||
|
const moveDoc = useCallback(
|
||||||
|
(nodeId: string, newParentId: string | null) => {
|
||||||
|
setDocs((prev) => {
|
||||||
|
const next = structuredClone(prev) as DocNode[];
|
||||||
|
const src = findNodeParentList(next, nodeId);
|
||||||
|
if (!src) return prev;
|
||||||
|
const [node] = src.list.splice(src.idx, 1);
|
||||||
|
if (newParentId === null) {
|
||||||
|
next.unshift(node);
|
||||||
|
} else {
|
||||||
|
const dst = findNodeParentList(next, newParentId);
|
||||||
|
if (dst && dst.list[dst.idx].type === "folder") {
|
||||||
|
const parent = dst.list[dst.idx];
|
||||||
|
parent.children = parent.children ?? [];
|
||||||
|
parent.children.unshift(node);
|
||||||
|
} else {
|
||||||
|
next.unshift(node);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
saveDocs(next);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
},
|
||||||
|
[findNodeParentList]
|
||||||
|
);
|
||||||
|
|
||||||
|
const updateDocContent = useCallback(
|
||||||
|
(nodeId: string, content: string) => {
|
||||||
|
setDocs((prev) => {
|
||||||
|
const next = structuredClone(prev) as DocNode[];
|
||||||
|
const found = findNodeParentList(next, nodeId);
|
||||||
|
if (found && found.list[found.idx].type === "doc") {
|
||||||
|
found.list[found.idx].content = content;
|
||||||
|
found.list[found.idx].updatedAt = Date.now();
|
||||||
|
}
|
||||||
|
saveDocs(next);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
},
|
||||||
|
[findNodeParentList]
|
||||||
|
);
|
||||||
|
|
||||||
|
const upsertDocCb = useCallback(
|
||||||
|
(_path: string[], node: DocNode) => {
|
||||||
|
setDocs((prev) => {
|
||||||
|
const next = structuredClone(prev) as DocNode[];
|
||||||
|
const found = findNodeParentList(next, node.id);
|
||||||
|
if (found) {
|
||||||
|
found.list[found.idx] = { ...node, updatedAt: Date.now() };
|
||||||
|
} else {
|
||||||
|
next.unshift({ ...node, updatedAt: Date.now() });
|
||||||
|
}
|
||||||
|
saveDocs(next);
|
||||||
|
return next;
|
||||||
|
});
|
||||||
|
},
|
||||||
|
[findNodeParentList]
|
||||||
|
);
|
||||||
|
|
||||||
|
// ===== 3D / 动作资产操作 =====
|
||||||
|
|
||||||
|
const upsertAsset3DCb = useCallback((a: Asset3D) => {
|
||||||
|
storeUpsertAsset3D(a);
|
||||||
|
setAssets3D(loadAssets3D());
|
||||||
|
}, []);
|
||||||
|
|
||||||
|
const deleteAsset3DCb = useCallback((id: string) => {
|
||||||
|
storeDeleteAsset3D(id);
|
||||||
|
setAssets3D(loadAssets3D());
|
||||||
|
}, []);
|
||||||
|
|
||||||
|
const upsertAssetMotionCb = useCallback((a: AssetMotion) => {
|
||||||
|
storeUpsertAssetMotion(a);
|
||||||
|
setAssetsMotion(loadAssetsMotion());
|
||||||
|
}, []);
|
||||||
|
|
||||||
|
const deleteAssetMotionCb = useCallback((id: string) => {
|
||||||
|
storeDeleteAssetMotion(id);
|
||||||
|
setAssetsMotion(loadAssetsMotion());
|
||||||
|
}, []);
|
||||||
|
|
||||||
const value = useMemo<AppContextValue>(
|
const value = useMemo<AppContextValue>(
|
||||||
() => ({
|
() => ({
|
||||||
sessions,
|
sessions,
|
||||||
@@ -440,6 +650,23 @@ export function AppProvider({ children }: { children: ReactNode }) {
|
|||||||
setSessionCharacterId,
|
setSessionCharacterId,
|
||||||
sessionAssetSpec,
|
sessionAssetSpec,
|
||||||
setSessionAssetSpec,
|
setSessionAssetSpec,
|
||||||
|
docs,
|
||||||
|
upsertDoc: upsertDocCb,
|
||||||
|
renameDoc,
|
||||||
|
deleteDoc,
|
||||||
|
moveDoc,
|
||||||
|
updateDocContent,
|
||||||
|
createDoc,
|
||||||
|
assets3D,
|
||||||
|
upsertAsset3D: upsertAsset3DCb,
|
||||||
|
deleteAsset3D: deleteAsset3DCb,
|
||||||
|
assetsMotion,
|
||||||
|
upsertAssetMotion: upsertAssetMotionCb,
|
||||||
|
deleteAssetMotion: deleteAssetMotionCb,
|
||||||
|
sessionTaskType,
|
||||||
|
setSessionTaskType,
|
||||||
|
commandPaletteOpen,
|
||||||
|
setCommandPaletteOpen,
|
||||||
}),
|
}),
|
||||||
[
|
[
|
||||||
sessions, activeSessionId, activeSession,
|
sessions, activeSessionId, activeSession,
|
||||||
@@ -453,6 +680,10 @@ export function AppProvider({ children }: { children: ReactNode }) {
|
|||||||
characters, upsertCharacterCb, deleteCharacterCb,
|
characters, upsertCharacterCb, deleteCharacterCb,
|
||||||
trainingTasks, upsertTrainingTaskCb, deleteTrainingTaskCb,
|
trainingTasks, upsertTrainingTaskCb, deleteTrainingTaskCb,
|
||||||
sessionStyleId, sessionCharacterId, sessionAssetSpec,
|
sessionStyleId, sessionCharacterId, sessionAssetSpec,
|
||||||
|
docs, upsertDocCb, renameDoc, deleteDoc, moveDoc, updateDocContent, createDoc,
|
||||||
|
assets3D, upsertAsset3DCb, deleteAsset3DCb,
|
||||||
|
assetsMotion, upsertAssetMotionCb, deleteAssetMotionCb,
|
||||||
|
sessionTaskType, commandPaletteOpen,
|
||||||
]
|
]
|
||||||
);
|
);
|
||||||
|
|
||||||
|
|||||||
@@ -11,6 +11,9 @@ import type {
|
|||||||
StylePack,
|
StylePack,
|
||||||
CharacterCard,
|
CharacterCard,
|
||||||
TrainingTask,
|
TrainingTask,
|
||||||
|
DocNode,
|
||||||
|
Asset3D,
|
||||||
|
AssetMotion,
|
||||||
} from "./types";
|
} from "./types";
|
||||||
import { getStoreUserId, generateId } from "./store";
|
import { getStoreUserId, generateId } from "./store";
|
||||||
|
|
||||||
@@ -345,3 +348,349 @@ export function upsertTrainingTask(t: TrainingTask) {
|
|||||||
export function deleteTrainingTask(id: string) {
|
export function deleteTrainingTask(id: string) {
|
||||||
saveTrainingTasks(loadTrainingTasks().filter((x) => x.id !== id));
|
saveTrainingTasks(loadTrainingTasks().filter((x) => x.id !== id));
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// ==================== 文档管理中心（占位文档树） ====================
|
||||||
|
|
||||||
|
const SAMPLE_DOC_WORLD = `# 大陆总览
|
||||||
|
|
||||||
|
这是一个占位世界观文档，用于展示文档中心的 Markdown 渲染能力。
|
||||||
|
|
||||||
|
## 地理分布
|
||||||
|
|
||||||
|
- **北境** — 终年积雪，古老贵族的封地
|
||||||
|
- **中原** — 商贸与战争的交汇之地
|
||||||
|
- **南境** — 湿热雨林，神秘原住部族
|
||||||
|
|
||||||
|
> "山川形便，人事因之；既有江河之险，亦有云雾之幽。"
|
||||||
|
|
||||||
|
## 关键王国
|
||||||
|
|
||||||
|
1. 艾萨王国（中原北部）
|
||||||
|
2. 赫利俄斯共和国（中原西侧）
|
||||||
|
3. 苍岚部族联盟（北境）
|
||||||
|
|
||||||
|
\`\`\`
|
||||||
|
示例代码块：
|
||||||
|
world.scale = 1024
|
||||||
|
world.season = "spring"
|
||||||
|
\`\`\`
|
||||||
|
|
||||||
|
## 关联资产
|
||||||
|
|
||||||
|
当你在项目里建立了角色/风格后，可以通过右侧面板或 \`@\` 键快捷引用：
|
||||||
|
|
||||||
|
[[asset:char-elica-swordsman]]
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*文档编辑器处于占位阶段，保存仅写入本地存储。*
|
||||||
|
`;
|
||||||
|
|
||||||
|
const SAMPLE_DOC_CHAR = `# 剑士·艾丽卡
|
||||||
|
|
||||||
|
[[asset:char-elica-swordsman]]
|
||||||
|
|
||||||
|
## 核心特征
|
||||||
|
|
||||||
|
- 银发紫瞳
|
||||||
|
- 红披风
|
||||||
|
- 双剑（左手短剑 + 右手长剑）
|
||||||
|
|
||||||
|
## 性格
|
||||||
|
|
||||||
|
**冷静**、果断、寡言。战斗中几乎不出声，只在谜题被揭破时轻笑一下。
|
||||||
|
|
||||||
|
## 背景故事（占位）
|
||||||
|
|
||||||
|
出身于北境贵族家庭，因家族变故而踏上旅途。她的双剑曾是母亲的遗物，现在由她继承并重新锻造。
|
||||||
|
|
||||||
|
## 出场台词
|
||||||
|
|
||||||
|
> "再叙旧怨，不如先把眼前的麻烦收拾干净。"
|
||||||
|
|
||||||
|
## 立绘要求
|
||||||
|
|
||||||
|
- **一致性级别**：高
|
||||||
|
- **必须保留特征**：银发、紫瞳、红披风、双剑
|
||||||
|
- **允许变化**：服饰细节、表情、动作
|
||||||
|
`;
|
||||||
|
|
||||||
|
const SAMPLE_DOC_PROMPT = `# 人物立绘 · 通用 Prompt 模板
|
||||||
|
|
||||||
|
## 正向 Prompt（骨架）
|
||||||
|
|
||||||
|
\`\`\`
|
||||||
|
masterpiece, best quality, highly detailed,
|
||||||
|
{character_description},
|
||||||
|
{action_pose},
|
||||||
|
{lighting},
|
||||||
|
{background}
|
||||||
|
\`\`\`
|
||||||
|
|
||||||
|
## 常用片段
|
||||||
|
|
||||||
|
### Lighting
|
||||||
|
|
||||||
|
- \`cinematic lighting, rim light, soft key light\`
|
||||||
|
- \`god rays, volumetric lighting, dust particles\`
|
||||||
|
|
||||||
|
### Background
|
||||||
|
|
||||||
|
- \`simple background, solid color\`
|
||||||
|
- \`ancient forest, mist, moss-covered ruins\`
|
||||||
|
|
||||||
|
## 负向 Prompt
|
||||||
|
|
||||||
|
\`\`\`
|
||||||
|
lowres, blurry, extra limbs, extra fingers,
|
||||||
|
deformed anatomy, watermark, signature, jpeg artifacts
|
||||||
|
\`\`\`
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
模板可在 Prompt 快选中直接应用（Phase 2）。
|
||||||
|
`;
|
||||||
|
|
||||||
|
const SAMPLE_DOC_SPEC = `# 项目输出规格
|
||||||
|
|
||||||
|
| 资产类型 | 分辨率 | 背景 | 其他 |
|
||||||
|
|---|---|---|---|
|
||||||
|
| Icon | 512×512 | 透明 | PNG |
|
||||||
|
| 角色立绘（全身） | 1024×1536 | 透明可选 | PNG |
|
||||||
|
| 场景 | 1920×1080 | 纯色/环境 | JPG/PNG |
|
||||||
|
| UI 元素 | 按需 | 透明 | PNG，@1x/@2x/@3x |
|
||||||
|
|
||||||
|
## 命名规范
|
||||||
|
|
||||||
|
\`{项目}_{资产类型}_{版本}_{序号}.{ext}\`
|
||||||
|
|
||||||
|
示例：\`epeekit_icon_v2_01.png\`
|
||||||
|
|
||||||
|
## 交付要求
|
||||||
|
|
||||||
|
- 命名遵循规范
|
||||||
|
- 保留图层源文件（psd/kra）可选
|
||||||
|
- 元数据（prompt/style/model）随资产入库
|
||||||
|
`;
|
||||||
|
|
||||||
|
export function loadDocs(): DocNode[] {
|
||||||
|
const list = readJSON<DocNode[]>(storageKey("docs"), []);
|
||||||
|
if (list.length === 0) {
|
||||||
|
const now = Date.now();
|
||||||
|
const defaults: DocNode[] = [
|
||||||
|
{
|
||||||
|
id: "doc-folder-world",
|
||||||
|
type: "folder",
|
||||||
|
name: "世界观",
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 0,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
children: [
|
||||||
|
{
|
||||||
|
id: "doc-world-overview",
|
||||||
|
type: "doc",
|
||||||
|
name: "大陆总览.md",
|
||||||
|
content: SAMPLE_DOC_WORLD,
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 0,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "doc-world-timeline",
|
||||||
|
type: "doc",
|
||||||
|
name: "历史纪年.md",
|
||||||
|
content: "# 历史纪年\n\n（占位文档，等待撰写）\n\n- 创世纪 0 年\n- 大分裂 412 年\n- 当前 1147 年",
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 1,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "doc-folder-chars",
|
||||||
|
type: "folder",
|
||||||
|
name: "角色档案",
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 1,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
children: [
|
||||||
|
{
|
||||||
|
id: "doc-char-elica",
|
||||||
|
type: "doc",
|
||||||
|
name: "剑士·艾丽卡.md",
|
||||||
|
content: SAMPLE_DOC_CHAR,
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 0,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "doc-folder-prompts",
|
||||||
|
type: "folder",
|
||||||
|
name: "Prompt 库",
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 2,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
children: [
|
||||||
|
{
|
||||||
|
id: "doc-prompt-char",
|
||||||
|
type: "doc",
|
||||||
|
name: "人物立绘通用.md",
|
||||||
|
content: SAMPLE_DOC_PROMPT,
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 0,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "doc-spec",
|
||||||
|
type: "doc",
|
||||||
|
name: "输出规格.md",
|
||||||
|
content: SAMPLE_DOC_SPEC,
|
||||||
|
projectId: DEFAULT_PROJECT_ID,
|
||||||
|
order: 3,
|
||||||
|
createdAt: now,
|
||||||
|
updatedAt: now,
|
||||||
|
},
|
||||||
|
];
|
||||||
|
writeJSON(storageKey("docs"), defaults);
|
||||||
|
return defaults;
|
||||||
|
}
|
||||||
|
return list;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function saveDocs(list: DocNode[]) {
|
||||||
|
writeJSON(storageKey("docs"), list);
|
||||||
|
}
|
||||||
|
|
||||||
|
// ==================== 3D 资产（占位） ====================
|
||||||
|
|
||||||
|
export function loadAssets3D(): Asset3D[] {
|
||||||
|
const list = readJSON<Asset3D[]>(storageKey("assets-3d"), []);
|
||||||
|
if (list.length === 0) {
|
||||||
|
const now = Date.now();
|
||||||
|
const defaults: Asset3D[] = [
|
||||||
|
{
|
||||||
|
id: "3d-sample-1",
|
||||||
|
thumbnail: "",
|
||||||
|
views: [0, 60, 120, 180, 240, 300].map((az) => ({
|
||||||
|
url: "",
|
||||||
|
azimuth: az,
|
||||||
|
elevation: 0,
|
||||||
|
})),
|
||||||
|
meshUrl: "placeholder.glb",
|
||||||
|
videoUrl: "",
|
||||||
|
prompt: "（占位）3D 角色立绘：银发剑士，卡通风格，6 视角",
|
||||||
|
pipeline: "trellis",
|
||||||
|
sessionId: undefined,
|
||||||
|
tags: [],
|
||||||
|
favorited: false,
|
||||||
|
createdAt: now - 3600000,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "3d-sample-2",
|
||||||
|
thumbnail: "",
|
||||||
|
views: [0, 90, 180, 270].map((az) => ({
|
||||||
|
url: "",
|
||||||
|
azimuth: az,
|
||||||
|
elevation: 15,
|
||||||
|
})),
|
||||||
|
meshUrl: "placeholder.glb",
|
||||||
|
prompt: "（占位）3D 道具：魔法剑，金属与宝石质感，4 视角",
|
||||||
|
pipeline: "hunyuan3d",
|
||||||
|
tags: [],
|
||||||
|
favorited: true,
|
||||||
|
createdAt: now - 86400000,
|
||||||
|
},
|
||||||
|
];
|
||||||
|
writeJSON(storageKey("assets-3d"), defaults);
|
||||||
|
return defaults;
|
||||||
|
}
|
||||||
|
return list;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function saveAssets3D(list: Asset3D[]) {
|
||||||
|
writeJSON(storageKey("assets-3d"), list);
|
||||||
|
}
|
||||||
|
|
||||||
|
export function upsertAsset3D(a: Asset3D) {
|
||||||
|
const list = loadAssets3D();
|
||||||
|
const idx = list.findIndex((x) => x.id === a.id);
|
||||||
|
if (idx >= 0) list[idx] = a;
|
||||||
|
else list.unshift(a);
|
||||||
|
saveAssets3D(list);
|
||||||
|
}
|
||||||
|
|
||||||
|
export function deleteAsset3D(id: string) {
|
||||||
|
saveAssets3D(loadAssets3D().filter((x) => x.id !== id));
|
||||||
|
}
|
||||||
|
|
||||||
|
// ==================== 动作/动画资产（占位） ====================
|
||||||
|
|
||||||
|
export function loadAssetsMotion(): AssetMotion[] {
|
||||||
|
const list = readJSON<AssetMotion[]>(storageKey("assets-motion"), []);
|
||||||
|
if (list.length === 0) {
|
||||||
|
const now = Date.now();
|
||||||
|
const defaults: AssetMotion[] = [
|
||||||
|
{
|
||||||
|
id: "motion-sample-1",
|
||||||
|
thumbnail: "",
|
||||||
|
frames: Array.from({ length: 16 }).map(() => ""),
|
||||||
|
videoUrl: "",
|
||||||
|
gifUrl: "",
|
||||||
|
fps: 12,
|
||||||
|
frameCount: 16,
|
||||||
|
loop: true,
|
||||||
|
duration: 16 / 12,
|
||||||
|
prompt: "（占位）艾丽卡挥剑动作，循环 1.3s",
|
||||||
|
model: "animatediff",
|
||||||
|
characterId: "char-elica-swordsman",
|
||||||
|
tags: [],
|
||||||
|
favorited: false,
|
||||||
|
createdAt: now - 7200000,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
id: "motion-sample-2",
|
||||||
|
thumbnail: "",
|
||||||
|
frames: Array.from({ length: 24 }).map(() => ""),
|
||||||
|
fps: 24,
|
||||||
|
frameCount: 24,
|
||||||
|
loop: false,
|
||||||
|
duration: 1,
|
||||||
|
prompt: "（占位）角色 idle 待机动作，1s",
|
||||||
|
model: "svd",
|
||||||
|
tags: [],
|
||||||
|
favorited: false,
|
||||||
|
createdAt: now - 86400000 * 2,
|
||||||
|
},
|
||||||
|
];
|
||||||
|
writeJSON(storageKey("assets-motion"), defaults);
|
||||||
|
return defaults;
|
||||||
|
}
|
||||||
|
return list;
|
||||||
|
}
|
||||||
|
|
||||||
|
export function saveAssetsMotion(list: AssetMotion[]) {
|
||||||
|
writeJSON(storageKey("assets-motion"), list);
|
||||||
|
}
|
||||||
|
|
||||||
|
export function upsertAssetMotion(a: AssetMotion) {
|
||||||
|
const list = loadAssetsMotion();
|
||||||
|
const idx = list.findIndex((x) => x.id === a.id);
|
||||||
|
if (idx >= 0) list[idx] = a;
|
||||||
|
else list.unshift(a);
|
||||||
|
saveAssetsMotion(list);
|
||||||
|
}
|
||||||
|
|
||||||
|
export function deleteAssetMotion(id: string) {
|
||||||
|
saveAssetsMotion(loadAssetsMotion().filter((x) => x.id !== id));
|
||||||
|
}
|
||||||
|
|||||||
@@ -223,3 +223,146 @@ export interface AnnotationData {
|
|||||||
/** canvas 导出的带标注截图（base64） */
|
/** canvas 导出的带标注截图（base64） */
|
||||||
snapshot?: string;
|
snapshot?: string;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// ==================== 文档管理中心（Phase 1） ====================
|
||||||
|
// 对应 INFOLAYER 扩展：非视觉资产的知识中枢（类 Cursor 工作区）。
|
||||||
|
|
||||||
|
/** 文档节点类型：文件夹 or 文件 */
|
||||||
|
export type DocNodeType = "folder" | "doc";
|
||||||
|
|
||||||
|
/** 文档树节点 */
|
||||||
|
export interface DocNode {
|
||||||
|
id: string;
|
||||||
|
type: DocNodeType;
|
||||||
|
name: string;
|
||||||
|
/** 仅 doc 生效：Markdown 源码 */
|
||||||
|
content?: string;
|
||||||
|
/** 仅 folder 生效：子节点 */
|
||||||
|
children?: DocNode[];
|
||||||
|
/** 所属项目 */
|
||||||
|
projectId?: string;
|
||||||
|
/** 用于排序的 sort 序号（同层级） */
|
||||||
|
order?: number;
|
||||||
|
createdAt: number;
|
||||||
|
updatedAt: number;
|
||||||
|
}
|
||||||
|
|
||||||
|
/** 已打开文档 Tab 的瞬态状态 */
|
||||||
|
export interface DocTabState {
|
||||||
|
nodeId: string;
|
||||||
|
/** 未保存修改的 buffer；undefined 表示已保存 */
|
||||||
|
dirtyContent?: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
// ==================== 3D 资产（Phase 2） ====================
|
||||||
|
|
||||||
|
/** 3D 视图（某个方位角 + 仰角的渲染结果） */
|
||||||
|
export interface View3D {
|
||||||
|
/** 相对路径或完整 URL */
|
||||||
|
url: string;
|
||||||
|
/** 方位角（度） */
|
||||||
|
azimuth: number;
|
||||||
|
/** 仰角（度） */
|
||||||
|
elevation: number;
|
||||||
|
/** 对应的法线图 URL（Mesh Pipeline Stage 2 输出） */
|
||||||
|
normalUrl?: string;
|
||||||
|
/** 对应的风格化后图 URL（Mesh Pipeline Stage 3 输出） */
|
||||||
|
restyledUrl?: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
/** 3D 模型资产 */
|
||||||
|
export interface Asset3D {
|
||||||
|
id: string;
|
||||||
|
/** 缩略图 */
|
||||||
|
thumbnail: string;
|
||||||
|
/** 多视图阵列 */
|
||||||
|
views: View3D[];
|
||||||
|
/** .glb 模型下载地址（占位） */
|
||||||
|
meshUrl?: string;
|
||||||
|
/** 360° 预览视频 URL（占位） */
|
||||||
|
videoUrl?: string;
|
||||||
|
/** 来源 prompt */
|
||||||
|
prompt: string;
|
||||||
|
/** 生成管道：trellis / hunyuan3d / zero123plus 等 */
|
||||||
|
pipeline: string;
|
||||||
|
/** 来源参考图（立绘/色彩稿）URL */
|
||||||
|
sourceImageUrl?: string;
|
||||||
|
sessionId?: string;
|
||||||
|
tags: string[];
|
||||||
|
favorited: boolean;
|
||||||
|
createdAt: number;
|
||||||
|
}
|
||||||
|
|
||||||
|
// ==================== 动作/动画资产（Phase 2） ====================
|
||||||
|
|
||||||
|
/** 动作序列资产 */
|
||||||
|
export interface AssetMotion {
|
||||||
|
id: string;
|
||||||
|
/** 缩略图（通常是首帧） */
|
||||||
|
thumbnail: string;
|
||||||
|
/** 所有帧的 URL 列表（占位） */
|
||||||
|
frames: string[];
|
||||||
|
/** 预览视频 URL（MP4） */
|
||||||
|
videoUrl?: string;
|
||||||
|
/** GIF URL（可选） */
|
||||||
|
gifUrl?: string;
|
||||||
|
/** 帧率 */
|
||||||
|
fps: number;
|
||||||
|
/** 帧数（= frames.length） */
|
||||||
|
frameCount: number;
|
||||||
|
/** 是否循环 */
|
||||||
|
loop: boolean;
|
||||||
|
/** 时长（秒） */
|
||||||
|
duration: number;
|
||||||
|
/** 来源 prompt */
|
||||||
|
prompt: string;
|
||||||
|
/** 使用模型：animatediff / svd / motion-lora 等 */
|
||||||
|
model: string;
|
||||||
|
/** 绑定的角色 ID（可选） */
|
||||||
|
characterId?: string;
|
||||||
|
/** 来源参考立绘 URL */
|
||||||
|
sourceImageUrl?: string;
|
||||||
|
sessionId?: string;
|
||||||
|
tags: string[];
|
||||||
|
favorited: boolean;
|
||||||
|
createdAt: number;
|
||||||
|
}
|
||||||
|
|
||||||
|
// ==================== 任务类型（Phase 2 扩展） ====================
|
||||||
|
|
||||||
|
/** 工作台当前任务类型（2D 图片 / 3D 模型 / 动作序列） */
|
||||||
|
export type TaskType = "image2d" | "model3d" | "motion";
|
||||||
|
|
||||||
|
/** 3D 生成参数（占位） */
|
||||||
|
export interface Params3D {
|
||||||
|
/** 管道 */
|
||||||
|
pipeline: "trellis" | "hunyuan3d" | "zero123plus";
|
||||||
|
/** 视图数 */
|
||||||
|
viewCount: number;
|
||||||
|
/** 方位角预设：equidistant / custom */
|
||||||
|
azimuthPreset: "equidistant" | "custom";
|
||||||
|
/** 自定义方位角列表（角度） */
|
||||||
|
customAzimuths?: number[];
|
||||||
|
/** 是否保持原图风格（IP-Adapter 风格还原） */
|
||||||
|
preserveStyle: boolean;
|
||||||
|
/** 分辨率（占位） */
|
||||||
|
resolution: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
/** 动作生成参数（占位） */
|
||||||
|
export interface ParamsMotion {
|
||||||
|
/** 模型 */
|
||||||
|
model: "animatediff" | "svd" | "motion-lora";
|
||||||
|
/** 帧数 */
|
||||||
|
frameCount: number;
|
||||||
|
/** 帧率 */
|
||||||
|
fps: number;
|
||||||
|
/** 是否循环 */
|
||||||
|
loop: boolean;
|
||||||
|
/** 输出格式 */
|
||||||
|
output: "mp4" | "gif" | "frames";
|
||||||
|
/** 绑定角色 ID */
|
||||||
|
characterId?: string;
|
||||||
|
/** 动作关键词（自然语言描述） */
|
||||||
|
motionHint?: string;
|
||||||
|
}
|
||||||
|
|||||||
1
art-agent/frontend/tsconfig.tsbuildinfo
Normal file
1
art-agent/frontend/tsconfig.tsbuildinfo
Normal file
File diff suppressed because one or more lines are too long
463
docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
Normal file
463
docs/art-agent/VIEW-TRANSFORM-MESH-PIPELINE-PLAN.md
Normal file
@@ -0,0 +1,463 @@
|
|||||||
|
# Mesh-Pipeline 视角变换 · 跨会话实施计划
|
||||||
|
|
||||||
|
> **状态**：SPEC / 尚未开工
|
||||||
|
> **最后更新**：2026-04-20 15:30
|
||||||
|
> **负责人**：Agent + 用户 @shine
|
||||||
|
> **适用对象**：任意新会话的 Agent，本文档自包含，无需额外上下文即可开工
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 0 · 上下文（Why）
|
||||||
|
|
||||||
|
### 0.1 起因
|
||||||
|
|
||||||
|
当前项目 `art-agent` 已经集成了 Zero123++（`jd7h/zero123plusplus`）做单图→多视角变换，但存在固有缺陷：
|
||||||
|
|
||||||
|
1. **只输出 6 个固定视角**，`azimuth/elevation` 写死在 `config.py`，用户无法指定任意相机位姿
|
||||||
|
2. **大角度一致性差**，Zero123++ 主要训练于小物体，对建筑类规整几何 + 大角度偏转常出现立面错位
|
||||||
|
3. **无几何中间产物**，纯图对图黑盒映射，无法二次利用
|
||||||
|
|
||||||
|
### 0.2 目标
|
||||||
|
|
||||||
|
新增一条"Mesh Pipeline"视角变换路径，与现有 `zero123plus` 并列保留，让用户可以：
|
||||||
|
|
||||||
|
- 输入 1 张 2D 图（典型场景：带描边卡通风的建筑，如教堂/房屋/塔楼）
|
||||||
|
- 输出 N 张**保留原画风**、**几何一致**的新视角 2D 图
|
||||||
|
- 可指定任意 `azimuth/elevation`（至少阶段性支持 Trellis 360° 中的任意角度）
|
||||||
|
|
||||||
|
**非目标**：输出 3D mesh 给用户下载（mesh 只是中间产物）；替代 Zero123++（它作为"轻量路径"继续保留）。
|
||||||
|
|
||||||
|
### 0.3 相关历史上下文
|
||||||
|
|
||||||
|
| 记录 | 说明 |
|
||||||
|
|---|---|
|
||||||
|
| `CL-20260416-1000` | Zero123++ 首次集成 |
|
||||||
|
| `CL-20260420-1212` | Zero123++ 切图布局修复（cols=2/rows=3） |
|
||||||
|
| `CL-20260420-1501` | 后端 watchfiles 依赖修复，uvicorn --reload 生效 |
|
||||||
|
| `PF-20260420-1212` | Grid 切图布局坑（"3×2" 措辞歧义） |
|
||||||
|
| `PF-20260420-1501` | Windows uvicorn --reload 无 watchfiles 退化坑 |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 1 · 核心决策
|
||||||
|
|
||||||
|
### 1.1 三段式流水线
|
||||||
|
|
||||||
|
```
|
||||||
|
[输入: 1 张 2D 图]
|
||||||
|
↓
|
||||||
|
【阶段 1】单图 3D 重建 → 生成 textured .glb + 预渲染 360° 视频
|
||||||
|
↓
|
||||||
|
【阶段 2】从视频抽帧 / 自定义相机渲染 → 多视角"几何参考图"
|
||||||
|
↓
|
||||||
|
【阶段 3】SDXL + ControlNet + IP-Adapter 二次重绘 → 还原原画风
|
||||||
|
↓
|
||||||
|
[输出: N 张保留风格、几何一致的 2D 新视角图]
|
||||||
|
```
|
||||||
|
|
||||||
|
### 1.2 模型选型
|
||||||
|
|
||||||
|
| 阶段 | 主选 | 备选 / 高级选项 | 理由 |
|
||||||
|
|---|---|---|---|
|
||||||
|
| 阶段 1 | **Trellis** (`firtoz/trellis`) | Hunyuan3D-2 (`tencent/hunyuan3d-2`) | Trellis $0.041/30s 且自带 color_video，Hunyuan 贵 3×慢 4×但 mesh 更扎实 |
|
||||||
|
| 阶段 2 | **ffmpeg 从 Trellis `color_video` 抽帧** | pyrender 加载 .glb 任意角度渲染 | Trellis 已送 360° 环绕视频，首版完全省事 |
|
||||||
|
| 阶段 3 | **`chigozienri/ip_adapter-sdxl-controlnet-depth`** | 自建 SDXL + 多 ControlNet 组合 | 一个 Replicate 模型打包了 SDXL+ControlNet-Depth+IP-Adapter |
|
||||||
|
|
||||||
|
### 1.3 为什么不用 Hunyuan3D-2 作默认
|
||||||
|
|
||||||
|
- 贵 3 倍（$0.12 vs $0.041）
|
||||||
|
- 慢 4 倍（127s vs 30s）
|
||||||
|
- **不返回预渲染视频** → 必须额外实现阶段 2（pyrender / blender 渲染器）
|
||||||
|
- 唯一优势：mesh 几何质量更高
|
||||||
|
|
||||||
|
→ 留作"高质量模式"供用户显式选择，一期不默认启用。
|
||||||
|
|
||||||
|
### 1.4 为什么不用 ControlNet-Depth 必须先估深度
|
||||||
|
|
||||||
|
`chigozienri/ip_adapter-sdxl-controlnet-depth` 的 `controlnet_input` 要求已经是 depth map。两条路：
|
||||||
|
|
||||||
|
- **路 A**：从 Trellis `normal_video` 抽帧，把 normal 当"结构约束"直接喂（近似方案，不完美但可用）
|
||||||
|
- **路 B**：从 color_video 抽帧后，额外调用 `chenxwh/depth-anything-v2` 生成 depth map
|
||||||
|
|
||||||
|
一期走路 A 简化；若效果不足再升级路 B（多一次 API 调用 + $0.003/张）。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 2 · 技术数据清单（Schema）
|
||||||
|
|
||||||
|
### 2.1 Trellis — `firtoz/trellis`
|
||||||
|
|
||||||
|
- **版本 ID**：`e8f6c45206993f297372f5436b90350817bd9b4a0d52d2a76df50c1c8afa2b3c`
|
||||||
|
- **成本**：$0.041/次（~24 次/$1）
|
||||||
|
- **耗时**：~30 秒
|
||||||
|
- **硬件**：Nvidia A100 80GB
|
||||||
|
- **输入关键字段**：
|
||||||
|
|
||||||
|
| 字段 | 类型 | 默认 | 说明 |
|
||||||
|
|---|---|---|---|
|
||||||
|
| `images` | `array[uri]` | 必填 | 输入图（支持多图，一期只传 1 张） |
|
||||||
|
| `seed` | int | 0 | 种子 |
|
||||||
|
| `randomize_seed` | bool | true | 一期设为 false 便于复现 |
|
||||||
|
| `texture_size` | int (512-2048) | 1024 | GLB 纹理分辨率 |
|
||||||
|
| `mesh_simplify` | float (0.9-0.98) | 0.95 | 网格简化，建议保持默认 |
|
||||||
|
| `generate_color` | bool | **true** | **必开**，用于得到 color_video |
|
||||||
|
| `generate_normal` | bool | **true** | **一期开启**，便于阶段 3 做结构约束 |
|
||||||
|
| `generate_model` | bool | **true** | **必开**，否则不输出 .glb |
|
||||||
|
| `save_gaussian_ply` | bool | false | 不需要 |
|
||||||
|
| `ss_sampling_steps` | int (1-50) | 12 | 默认即可 |
|
||||||
|
| `slat_sampling_steps` | int (1-50) | 12 | 默认即可 |
|
||||||
|
| `ss_guidance_strength` | float (0-10) | 7.5 | 默认即可 |
|
||||||
|
| `slat_guidance_strength` | float (0-10) | 3 | 默认即可 |
|
||||||
|
|
||||||
|
- **输出字段**（⚠️ 实测修订 2026-04-20 16:15，版本 `e8f6c452...`）：
|
||||||
|
|
||||||
|
| 字段 | 类型 | 实测行为 |
|
||||||
|
|---|---|---|
|
||||||
|
| `model_file` | uri | ✅ .glb 文件（`generate_model=true` 时）|
|
||||||
|
| `color_video` | uri | ❌ **恒为 null** — 该部署版不单独输出 |
|
||||||
|
| `normal_video` | uri | ❌ **恒为 null** — 该部署版不单独输出 |
|
||||||
|
| `combined_video` | uri | ✅ **唯一可用的视频** — color+normal **左右并排** mp4 |
|
||||||
|
| `gaussian_ply` | uri | ✅ 高斯点云（本项目不用） |
|
||||||
|
| `no_background_images` | array[uri] | ✅ 去背景的预处理图 |
|
||||||
|
|
||||||
|
**实测 schema 踩坑**（已记为 PF-20260420-1600）：
|
||||||
|
|
||||||
|
1. 输入字段必须用 `images`（数组）—— 传 `image`（单数字符串）会 422 `input: images is required`，即使 Replicate README example 里写的是 `image`。
|
||||||
|
2. 尽管 `generate_color=True` 和 `generate_normal=True` 都开，`color_video` 和 `normal_video` 字段也**恒为 null**，只有 `combined_video` 可用。
|
||||||
|
3. 因此 Phase 2 抽帧的数据源是 `combined_video`，抽帧后需要**切左半 = color 帧、切右半 = normal 帧**。
|
||||||
|
|
||||||
|
### 2.2 Hunyuan3D-2 — `tencent/hunyuan3d-2`（备选）
|
||||||
|
|
||||||
|
- **版本 ID**：`b1b9449a1277e10402781c5d41eb30c0a0683504fb23fab591ca9dfc2aabe1cb`
|
||||||
|
- **成本**：$0.12/次
|
||||||
|
- **耗时**：~127 秒
|
||||||
|
- **硬件**：Nvidia L40S
|
||||||
|
- **输入**：`image`, `steps` (20-50, default 50), `guidance_scale` (1-20, default 5.5), `seed`, `octree_resolution` (default 256), `remove_background` (default true)
|
||||||
|
- **输出**：`mesh` (uri, .glb) —— **无视频无多视角预览**，必须配套阶段 2 自定义渲染
|
||||||
|
|
||||||
|
### 2.3 ControlNet + IP-Adapter — `chigozienri/ip_adapter-sdxl-controlnet-depth`
|
||||||
|
|
||||||
|
- **版本 ID**：`0436c8702ef52616be5c30948551b3af6a86c821cca9b01f11ac297624fff14c`
|
||||||
|
- **成本**：$0.070/次
|
||||||
|
- **耗时**：~72 秒
|
||||||
|
- **硬件**：Nvidia L40S
|
||||||
|
- **输入关键字段**：
|
||||||
|
|
||||||
|
| 字段 | 类型 | 默认 | 说明 |
|
||||||
|
|---|---|---|---|
|
||||||
|
| `image` | uri | 必填 | **IP-Adapter 参考图**（此处传**用户原图**保持风格） |
|
||||||
|
| `controlnet_input` | uri | 必填 | **Depth / Normal / Lineart 参考图**（此处传**阶段 2 抽出来的 normal 帧**） |
|
||||||
|
| `scale` | float (0-1) | 0.6 | IP-Adapter 权重，建议调到 **0.7-0.8** 强化风格 |
|
||||||
|
| `controlnet_conditioning_scale` | float (0-1) | 0.6 | 结构约束权重，建议 **0.7-0.9** |
|
||||||
|
| `prompt` | str | "" | 留空或用 "same building, same art style" |
|
||||||
|
| `negative_prompt` | str | "" | "blurry, distorted, different style" |
|
||||||
|
| `num_outputs` | int (1-4) | 1 | 一期 1 |
|
||||||
|
| `num_inference_steps` | int (1-500) | 30 | 默认即可 |
|
||||||
|
| `seed` | int | 随机 | 调参阶段固定 |
|
||||||
|
|
||||||
|
### 2.4 依赖清单
|
||||||
|
|
||||||
|
**一期必装**（首版走 Trellis + ffmpeg 抽帧，最小化依赖）：
|
||||||
|
|
||||||
|
```
|
||||||
|
# backend requirements.txt
|
||||||
|
ffmpeg-python==0.2.0 # 或者直接在后端宿主机装 ffmpeg 可执行文件
|
||||||
|
```
|
||||||
|
|
||||||
|
**二期可选**（若要上 Hunyuan3D-2 + 自定义相机）：
|
||||||
|
|
||||||
|
```
|
||||||
|
trimesh==4.5.0
|
||||||
|
pyrender==0.1.45
|
||||||
|
PyOpenGL==3.1.7
|
||||||
|
# Windows 额外需要 OSMesa 或改用 Blender headless（二选一）
|
||||||
|
```
|
||||||
|
|
||||||
|
**系统依赖**：
|
||||||
|
|
||||||
|
- `ffmpeg` 可执行文件（Windows：`choco install ffmpeg` 或手动放 PATH）
|
||||||
|
- 若二期启用：Windows 上 OSMesa 编译困难，推荐用 Blender 4.x headless 替代
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 3 · 数据流与接口设计
|
||||||
|
|
||||||
|
### 3.1 新增后端服务模块
|
||||||
|
|
||||||
|
```
|
||||||
|
art-agent/backend/app/services/
|
||||||
|
├── view_transform.py # [改造] 管道调度器
|
||||||
|
├── mesh_generator.py # [新增] 阶段 1：调用 Trellis / Hunyuan3D-2
|
||||||
|
├── video_frame_extractor.py # [新增] 阶段 2（轻量）：ffmpeg 抽帧
|
||||||
|
├── mesh_renderer.py # [新增, 二期] 阶段 2（自由相机）：pyrender 加载 .glb 渲染任意角度
|
||||||
|
└── style_restorer.py # [新增] 阶段 3：ControlNet + IP-Adapter 重绘
|
||||||
|
```
|
||||||
|
|
||||||
|
### 3.2 管道调度伪代码
|
||||||
|
|
||||||
|
```python
|
||||||
|
# services/view_transform.py
|
||||||
|
async def transform_view_mesh_pipeline(
|
||||||
|
image_path: str,
|
||||||
|
model_id: str = "trellis", # or "hunyuan3d"
|
||||||
|
azimuths: list[int] = [0, 60, 120, 180, 240, 300],
|
||||||
|
elevations: list[int] = [0, 0, 0, 0, 0, 0],
|
||||||
|
preserve_style: bool = True, # 是否走阶段 3
|
||||||
|
) -> dict:
|
||||||
|
# === 阶段 1 ===
|
||||||
|
mesh_result = await mesh_generator.generate(image_path, model_id)
|
||||||
|
# 返回 {glb_url, color_video_url?, normal_video_url?}
|
||||||
|
|
||||||
|
# === 阶段 2 ===
|
||||||
|
if model_id == "trellis":
|
||||||
|
# 从视频抽帧（Trellis 的 360° 视频约 5s，对应 az 0→360°）
|
||||||
|
frames = await video_frame_extractor.extract_by_azimuth(
|
||||||
|
color_video_url=mesh_result["color_video_url"],
|
||||||
|
normal_video_url=mesh_result["normal_video_url"],
|
||||||
|
azimuths=azimuths,
|
||||||
|
total_rotation_deg=360,
|
||||||
|
)
|
||||||
|
else: # hunyuan3d
|
||||||
|
# 二期：自定义相机渲染
|
||||||
|
frames = await mesh_renderer.render_views(
|
||||||
|
glb_path=mesh_result["glb_path"],
|
||||||
|
azimuths=azimuths,
|
||||||
|
elevations=elevations,
|
||||||
|
)
|
||||||
|
# frames = [{az, el, color_png, normal_png}, ...]
|
||||||
|
|
||||||
|
# === 阶段 3 ===
|
||||||
|
if preserve_style:
|
||||||
|
final_images = await asyncio.gather(*[
|
||||||
|
style_restorer.restore(
|
||||||
|
original_image=image_path,
|
||||||
|
structure_image=f["normal_png"],
|
||||||
|
azimuth=f["az"],
|
||||||
|
elevation=f["el"],
|
||||||
|
)
|
||||||
|
for f in frames
|
||||||
|
])
|
||||||
|
else:
|
||||||
|
final_images = [f["color_png"] for f in frames]
|
||||||
|
|
||||||
|
return {
|
||||||
|
"success": True,
|
||||||
|
"images": [
|
||||||
|
{"url": img, "azimuth": az, "elevation": el}
|
||||||
|
for img, (az, el) in zip(final_images, zip(azimuths, elevations))
|
||||||
|
],
|
||||||
|
"mesh_url": mesh_result.get("glb_url"),
|
||||||
|
"model_name": f"Mesh Pipeline ({model_id})",
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
### 3.3 config.py 扩展
|
||||||
|
|
||||||
|
```python
|
||||||
|
VIEW_TRANSFORM_MODELS = {
|
||||||
|
"zero123plus": {...}, # 保留不动
|
||||||
|
"trellis": {
|
||||||
|
"id": "trellis",
|
||||||
|
"name": "Trellis (Mesh Pipeline)",
|
||||||
|
"provider": "replicate",
|
||||||
|
"model_id": "firtoz/trellis:e8f6c45206993f297372f5436b90350817bd9b4a0d52d2a76df50c1c8afa2b3c",
|
||||||
|
"description": "3D 重建 + 任意视角 + 风格还原，建筑友好（~30s + 风格化 ~72s/张）",
|
||||||
|
"pipeline": "mesh", # 新增字段区分管道类型
|
||||||
|
"default_params": {
|
||||||
|
"texture_size": 1024,
|
||||||
|
"mesh_simplify": 0.95,
|
||||||
|
"generate_color": True,
|
||||||
|
"generate_normal": True,
|
||||||
|
"generate_model": True,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
"hunyuan3d": {
|
||||||
|
"id": "hunyuan3d",
|
||||||
|
"name": "Hunyuan3D-2 (高质量)",
|
||||||
|
"provider": "replicate",
|
||||||
|
"model_id": "tencent/hunyuan3d-2:b1b9449a1277e10402781c5d41eb30c0a0683504fb23fab591ca9dfc2aabe1cb",
|
||||||
|
"description": "几何质量最佳（~127s），需自定义渲染（二期启用）",
|
||||||
|
"pipeline": "mesh",
|
||||||
|
"enabled": False, # 一期先禁用
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
IMAGE_MODELS["ip-adapter-controlnet-depth"] = {
|
||||||
|
"id": "ip-adapter-controlnet-depth",
|
||||||
|
"name": "IP-Adapter + ControlNet Depth (内部)",
|
||||||
|
"provider": "replicate",
|
||||||
|
"model_id": "chigozienri/ip_adapter-sdxl-controlnet-depth:0436c8702ef52616be5c30948551b3af6a86c821cca9b01f11ac297624fff14c",
|
||||||
|
"internal": True, # 不在前端展示，仅用于阶段 3
|
||||||
|
...
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
### 3.4 工具层 `tools.py`
|
||||||
|
|
||||||
|
`transform_view` 工具参数扩展（向后兼容）：
|
||||||
|
|
||||||
|
```python
|
||||||
|
{
|
||||||
|
"name": "transform_view",
|
||||||
|
"parameters": {
|
||||||
|
"image_path": {...},
|
||||||
|
"model_id": {
|
||||||
|
"enum": ["zero123plus", "trellis", "hunyuan3d"],
|
||||||
|
"default": "zero123plus",
|
||||||
|
},
|
||||||
|
# 以下为 mesh pipeline 专属参数
|
||||||
|
"azimuths": {"type": "array", "default": [0, 60, 120, 180, 240, 300]},
|
||||||
|
"elevations": {"type": "array", "default": [0, 0, 0, 0, 0, 0]},
|
||||||
|
"preserve_style": {"type": "boolean", "default": True},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
### 3.5 前端改造
|
||||||
|
|
||||||
|
- 模型下拉增加 "Trellis (Mesh Pipeline)" 和 "Hunyuan3D-2 (高质量)" 选项
|
||||||
|
- 选中 mesh pipeline 时，额外显示：
|
||||||
|
- "保留原画风格" 开关（默认开）
|
||||||
|
- 角度输入：简化为"快速预设（6/8/12 视角）" + "自定义 azimuth 数组"（高级）
|
||||||
|
- 结果区域：除了 N 张图，还展示 `color_video` 可预览
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 4 · 施工任务清单（跨会话可独立执行）
|
||||||
|
|
||||||
|
### Phase 1：Trellis 接入（预计 1.5h）
|
||||||
|
|
||||||
|
**验收标准**：用 curl / Replicate SDK 能跑通一次 Trellis，拿到 .glb + color_video URL，下载到本地。
|
||||||
|
|
||||||
|
- [x] P1-1 `services/mesh_generator.py` 新建，封装 `generate_with_trellis(image_path)` 函数（调用 Replicate + 下载结果到 `GENERATED_DIR`）
|
||||||
|
- [x] P1-2 `config.py` 新增 `VIEW_TRANSFORM_MODELS["trellis"]` 条目
|
||||||
|
- [x] P1-3 `services/view_transform.py` 根据 `pipeline == "mesh"` 分流到 `mesh_generator`
|
||||||
|
- [x] P1-4 `tools.py` 的 `transform_view` 增加 `model_id` 参数默认值兼容
|
||||||
|
- [x] P1-5 本地手动测试：`scripts/test_trellis.py` 可独立运行验证 Trellis → .glb + color_video + normal_video 本地落地（**等用户执行**）
|
||||||
|
|
||||||
|
### Phase 2：ffmpeg 抽帧（预计 1h）
|
||||||
|
|
||||||
|
**验收标准**：从 color_video.mp4 抽出指定 azimuth 对应的帧，保存为 PNG，帧数正确、角度映射正确。
|
||||||
|
|
||||||
|
- [x] P2-1 宿主机 ffmpeg 未装，改用 `imageio-ffmpeg==0.5.1`（静态二进制随包，免系统依赖），已写入 `requirements.txt`
|
||||||
|
- [x] P2-2 `services/video_frame_extractor.py` 新建，实现 `extract_by_azimuth(combined_video_path, azimuths, elevations=None, total_rotation_deg=360)`
|
||||||
|
- 策略改为"一次抽全帧到 temp dir + 按帧索引挑" —— 比 `-ss` 逐帧抽更稳（不受 keyframe 对齐影响），且 5s 视频成本可忽略
|
||||||
|
- 抽出后用 PIL 按中线切：左半 → color_png、右半 → normal_png（实测 1024×512 → 512×512 方形）
|
||||||
|
- `ffmpeg + PIL` 是阻塞的，用 `run_in_executor` 丢到线程池避免堵住 async 事件循环
|
||||||
|
- 临时目录抽完即清理，只保留切好的最终帧
|
||||||
|
- [x] P2-3 `view_transform._transform_view_mesh` 串接 Stage 1 → Stage 2：默认 `azimuths=[0,60,120,180,240,300]`；Stage 2 失败不会把整体置为失败（Stage 1 的 .glb / video 仍有交付价值，`error` 字段单独带回 Stage 2 错误）
|
||||||
|
- [x] P2-4 本地测试脚本 `scripts/test_frame_extract.py`（**等用户执行**验收）
|
||||||
|
- Agent 已自测：120 帧视频 → az=0/60/120/180/240/300 映射到 frame_idx=0/20/40/60/80/100，完全均匀 ✓
|
||||||
|
- 12 个 color/normal PNG 全部落盘，尺寸 512×512 方形 ✓
|
||||||
|
|
||||||
|
### Phase 3：风格还原重绘（预计 1.5h）
|
||||||
|
|
||||||
|
**验收标准**：6 张视角图通过 IP-Adapter+ControlNet 重绘后，风格与原图一致、几何不变形。
|
||||||
|
|
||||||
|
- [x] P3-1 `config.py` 注册 `IMAGE_MODELS["ip-adapter-controlnet-depth"]`，标 `internal=True`，同时改 `get_image_models_list()` 过滤 internal，不污染前端下拉
|
||||||
|
- [x] P3-2 `services/style_restorer.py` 新建，实现 `restore(original_image, structure_image, ...)` + `restore_batch()`（带并发 Semaphore 防 Replicate rate limit）
|
||||||
|
- [x] P3-3 `view_transform.py` 增加阶段 3；`preserve_style=True` 时对 Stage 2 的每一帧做重绘；单帧失败自动回退为 Stage 2 color 帧，不阻塞整体
|
||||||
|
- [ ] P3-4 **等待 Checkpoint 3**：调参轮次需要用户执行 `scripts/test_style_restore.py <原图>`，分别尝试 `scale=0.6/0.7/0.8` × `controlnet_conditioning_scale=0.6/0.7/0.9`，选出最佳组合写入默认参数
|
||||||
|
|
||||||
|
### Phase 4：前端 + 端到端联调（预计 1h）
|
||||||
|
|
||||||
|
- [ ] P4-1 `types.ts` 扩展 `ViewTransformModel` 类型
|
||||||
|
- [ ] P4-2 前端模型下拉新增两个选项
|
||||||
|
- [ ] P4-3 工作台选中 mesh 管道时显示"保留原画风"开关
|
||||||
|
- [ ] P4-4 结果面板支持展示视频（color_video）+ N 张风格化后的视角图
|
||||||
|
- [ ] P4-5 端到端联调：前端上传一张卡通建筑图 → 选 Trellis → 确认 N 张结果正确显示
|
||||||
|
|
||||||
|
### Phase 5：Hunyuan3D-2 + 自由相机（**可选，二期**，预计 3-4h）
|
||||||
|
|
||||||
|
**仅在 Phase 1-4 完成且用户明确要求自由 elevation/远近相机时启动。**
|
||||||
|
|
||||||
|
- [ ] P5-1 venv 安装 `trimesh + pyrender + PyOpenGL`；Windows 上验证 headless 可用性
|
||||||
|
- [ ] P5-2 若 pyrender 在 Windows 不可行 → 改用 Blender 4.x headless（需 `blender.exe -b --python render.py`）
|
||||||
|
- [ ] P5-3 `services/mesh_renderer.py` 新建，实现 `render_views(glb_path, azimuths, elevations, distance=2.0, fov=45)`
|
||||||
|
- [ ] P5-4 启用 `config.py` 的 `hunyuan3d` 条目（`enabled=True`）
|
||||||
|
- [ ] P5-5 前端"高级模式"解锁 elevation 滑块
|
||||||
|
|
||||||
|
### Phase 6：收尾
|
||||||
|
|
||||||
|
- [ ] P6-1 `changelog-full.md` / `-recent.md` / `-headlines.md` 三层同步记录
|
||||||
|
- [ ] P6-2 发现的坑 → `pitfalls.md`
|
||||||
|
- [ ] P6-3 更新 `art-agent/README.md` 里视角变换段落
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 5 · 风险与兜底
|
||||||
|
|
||||||
|
| 风险 | 概率 | 影响 | 兜底 |
|
||||||
|
|---|---|---|---|
|
||||||
|
| Trellis 对 2D 卡通描边图重建几何偏糊 | 中 | 阶段 3 结构约束失效 | 先用 SDXL+InstantStyle 把原图"半写实化"一版给 Trellis 吃，最后阶段 3 用原 2D 图做 IP-Adapter 还原风格 |
|
||||||
|
| 从 color_video 抽帧只有水平环绕（elevation=0），不能仰视/俯视 | 高 | 无法满足"仰视大教堂"等需求 | 二期启用 Phase 5 的 pyrender 自由相机，或改用 Hunyuan3D-2 + 自定义渲染 |
|
||||||
|
| IP-Adapter+ControlNet 6 次调用并发打满 Replicate rate limit | 低 | 部分帧失败 | 改成串行 + 指数退避 + 失败单帧重试 |
|
||||||
|
| 总链路太慢（>3 分钟）用户失去耐心 | 中 | 产品体验差 | 前端用 SSE 流式展示中间产物：阶段 1 完成显示视频 → 阶段 3 每张完成立即插入 |
|
||||||
|
| ffmpeg 未装 | 高（Windows） | Phase 2 不能跑 | 开工前检查 `ffmpeg -version`，未装先 `choco install ffmpeg` 或用 Python 库 `imageio-ffmpeg` 绑定 |
|
||||||
|
| Trellis 某次输出 video 是 4s 某次 6s，固定 total_rotation_deg=360 可能不准 | 低 | 抽帧角度偏差 | 用 `ffprobe` 动态读取总帧数；如有疑问就固定 24 帧均匀抽样全部保留 |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 6 · 成本与性能预估
|
||||||
|
|
||||||
|
**一次完整请求（6 视角，保留风格）**：
|
||||||
|
|
||||||
|
| 阶段 | 耗时 | 成本 |
|
||||||
|
|---|---|---|
|
||||||
|
| Trellis 重建 | ~30s | $0.041 |
|
||||||
|
| ffmpeg 抽 6 帧 | ~2s（本地） | 0 |
|
||||||
|
| ControlNet+IP-Adapter × 6（并发） | ~72s | $0.42 |
|
||||||
|
| **合计** | **~105s** | **~$0.46** |
|
||||||
|
|
||||||
|
参考：当前 Zero123++ 一次 ~$0.02，~15s。新管道贵约 23×、慢约 7×，但产出质量对建筑是跨代提升。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 7 · 跨会话恢复指引
|
||||||
|
|
||||||
|
**新会话的 Agent 在开工前务必**：
|
||||||
|
|
||||||
|
1. 读本文件 **§0-§3**，建立完整技术背景
|
||||||
|
2. 读 `art-agent/backend/app/services/view_transform.py` 当前实现（Zero123++ 的做法作参照）
|
||||||
|
3. 读 `art-agent/backend/app/config.py` 的 `VIEW_TRANSFORM_MODELS` / `IMAGE_MODELS` 当前结构
|
||||||
|
4. 读 `art-agent/backend/app/agent/tools.py` 看 `transform_view` 工具定义
|
||||||
|
5. 按 **§4 的 Phase 顺序**推进，Phase 之间互相独立，完成一个交付一个
|
||||||
|
6. 每个 Phase 完成后在本文件对应 checkbox 打勾（改 `[ ]` 为 `[x]`），并在本节底部追加简短进度 note
|
||||||
|
|
||||||
|
**不要一次 Phase 1-6 全做完再交付**——每个 Phase 完成后停下来让用户测试/审阅。
|
||||||
|
|
||||||
|
### 进度日志
|
||||||
|
|
||||||
|
<!-- 格式：YYYY-MM-DD 会话简述 → 完成了 Px-y 的哪些 item -->
|
||||||
|
|
||||||
|
- 2026-04-20 · 会话"Zero123++ 切图诊断 + 方案调研" → 完成 §2 全部 schema 查证，写入本 SPEC。尚未开工 Phase 1。
|
||||||
|
- 2026-04-20 · 会话"按计划实施 Mesh Pipeline" → 完成 Phase 1（P1-1 ~ P1-5）：新增 `mesh_generator.py`、`config.py` 注册 trellis/hunyuan3d（后者 enabled=False）、`view_transform.py` 按 `pipeline` 字段分流、`tools.py` 扩 `model_id/azimuths/preserve_style` 参数，额外提供 `scripts/test_trellis.py` 供用户手动验收。
|
||||||
|
- 2026-04-20 16:15 · **Checkpoint 1 通过** → Agent 运行 `scripts/test_trellis.py` 实测发现：
|
||||||
|
- ✅ Trellis 调用链路完全打通：Replicate token / 代理 / httpx 下载 / GENERATED_DIR 落盘均正常
|
||||||
|
- ✅ `.glb` (1.89MB) 下载正常
|
||||||
|
- ⚠️ 意外发现：该部署版 `color_video` / `normal_video` 字段**恒为 null**，只有 `combined_video` 可用（color+normal 左右并排 mp4 ~450KB）
|
||||||
|
- 修订 §2.1 输出字段表为实测版本，P2-2 任务改为"从 combined_video 抽帧 + 切左右半"，已记 PF-20260420-1600 踩坑
|
||||||
|
- Phase 1 verdict：**functionally green**，可以开 Phase 2
|
||||||
|
- 2026-04-20 · 会话"继续执行 Phase 2" → 完成 Phase 2 全部 item（P2-1 ~ P2-4）：
|
||||||
|
- 放弃系统 ffmpeg，改用 `imageio-ffmpeg` 自带二进制（22.6MB wheel，Win amd64 下已测 v4.2.2 ok）
|
||||||
|
- 新增 `services/video_frame_extractor.py` — 一次全帧抽取 + 按索引挑 + PIL 切左右半的极简实现
|
||||||
|
- `view_transform.py` 的 mesh 管道调度器现已走到 Stage 2，返回的 `images[]` 含 `{url, azimuth, elevation, normal_url, frame_idx}`
|
||||||
|
- 新增 `scripts/test_frame_extract.py` 供用户复用已有 combined_video 做 Checkpoint 2 验收（无需再花钱跑 Trellis）
|
||||||
|
- Agent 自测：120 帧 → 6 视角 frame_idx 均匀分布 (0/20/40/60/80/100)，所有切图 512×512 方形，逻辑正确
|
||||||
|
- **等待 Checkpoint 2 用户验收**：跑 `python scripts/test_frame_extract.py` 并目视检查 `generated/view_*_color.png` 6 张图的角度顺序
|
||||||
|
- 2026-04-20 · 会话"继续执行 Phase 3（风格还原）" → 完成 P3-1 ~ P3-3：
|
||||||
|
- `config.py` 注册内部模型 `ip-adapter-controlnet-depth`（`internal=True`），并让 `get_image_models_list()` 自动过滤，不会污染前端下拉；新增 helper `get_style_restore_model_id()`
|
||||||
|
- 新增 `services/style_restorer.py`：`restore()` 单帧调用 + `restore_batch()` 带 Semaphore 并发 3 的批量接口；统一处理 FileOutput/list/str 的 Replicate 返回
|
||||||
|
- `view_transform._transform_view_mesh` 接入 Stage 3：当 `preserve_style=True` 对每一帧做 IP-Adapter+ControlNet 重绘；**单帧失败会自动回退为 Stage 2 color 帧**，不阻塞整体；`images[i]` 新增 `restyled` 布尔和 `color_url`（保留原 color 便于对比）
|
||||||
|
- 最终返回的 `_stage` 字段从 `stage2` 升级为 `stage3 (N/M restyled)`，便于前端 / 日志快速判断链路完整度
|
||||||
|
- 新增 `scripts/test_style_restore.py` 供 Checkpoint 3 用户验收：支持 `--single` 冒烟、`--prefix` 指定 normal 帧组、`--scale/--cn-scale` 覆盖参数，复用 Phase 2 已有帧无需再跑 Trellis
|
||||||
|
- **等待 Checkpoint 3 用户验收**：跑 `python scripts/test_style_restore.py <原图> --single` 做冒烟，通过后再全量 6 帧并调参（P3-4）
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 8 · 开放问题（留给未来决策）
|
||||||
|
|
||||||
|
- 前端角度输入 UX：要不要做一个"3D 预览转盘"让用户拖动选角度？（Phase 4+ 再说）
|
||||||
|
- 是否把 mesh `.glb` 作为资产保存到用户的 gallery？（涉及存储与用户系统对接）
|
||||||
|
- Hunyuan3D-2 路线的 Windows 渲染器：pyrender vs Blender 的选型需要一次实测才能决定
|
||||||
|
- 是否对同一原图的重复请求加缓存？（Trellis 结果相对稳定，可按 image_hash 缓存 .glb）
|
||||||
Reference in New Issue
Block a user