* docs(readme): match the product website's look and drop slogan copy Add hero and capability-card artwork (English and Chinese, light and dark) drawn in the website's palette, type and line icons, plus small gold table icons; docs/images/readme/src/generate.py rebuilds them. The copy in the artwork is the homepage's own. Replace per-bullet emoji and slogan-style lead-ins with plain labels, drop emoji from headings and captions, add the homepage's three ways to get started and the v0.8.2 product shots, restyle the badges in the brand colors, and give the client table real logos or consistent line icons. * docs(readme): bring JA/KO in line and add feature spotlights Rebuild README_JA.md and README_KO.md on the same structure as the English and Chinese READMEs, keeping their existing translations. Add what they were missing: CLI and Mini Program entries, the contribution validation steps, knowledge graph, access control and security rows, Zhipu embeddings and Tencent Cloud COS. README_KO keeps its usage scenarios. Generate Japanese and Korean hero and capability artwork with language-specific CJK fonts, so Japanese kanji do not fall back to Chinese glyph forms and Hangul wraps at spaces. Replace the flat screenshot grid with four spotlights (local browser, skills and sandbox, automatic wiki, observability), each pairing two real screenshots in window frames; the remaining shots move to a two-column "more screenshots" grid. docs/images/readme/src/spotlights.py rebuilds the spotlight images. * docs(readme): keep the browser task preview visible in its spotlight The browser-connection window sat in the bottom-right corner, right over the in-chat task preview that the main screenshot is meant to show. Let each spotlight pick the corner for its side window and put the browser one bottom-left, over the session list instead. * docs(readme): make spotlight images clickable and sharp when opened GitHub links a bare <img> to the full image but leaves <picture> inert, so the spotlights could not be opened. Wrap each one in a link to its image, and write the spotlights at 3200x1800 so the screenshots are readable at full size and crisp on high-density displays. * docs(readme): add Q&A and toolbox spotlights, drop the leftover screenshots Add two spotlights: quick Q&A beside smart reasoning, and the toolbox's MCP service tools beside its skill catalog. They cover the Q&A and skill catalog shots from the screenshot grid, so the grid and its remaining chunk editing, folder tree and wiki revision shots go. * docs(readme): redraw the architecture diagram and widen the hero highlights Replace docs/images/architecture.png with a generated diagram in the same visual language as the rest of the README (per language, light and dark), drawn from website-docs/02-architecture: clients and channels feed the Go app, where RAG Q&A, agent reasoning and auto wiki share one knowledge pipeline over workspaces, the model catalog, the task queue and tracing; the app calls docreader, sandboxes, model providers, web search, external MCP services and data sources, and stores data in PostgreSQL (ParadeDB), Redis and the optional vector, object, Neo4j and Langfuse stores. The old PNG was only referenced by the READMEs. The hero listed only the three core modes; show eight highlights instead (adding the local browser, skills and sandbox, MCP Server, long-term memory, and data sources and IM) so the first screen reflects the product's range. The capability cards below still explain the three core modes. |
||
|---|---|---|
| .. | ||
| assets | ||
| images | ||
| poc/docker-sandbox | ||
| LITE.md | ||
| README.md | ||
| docs.go | ||
| swagger.json | ||
| swagger.yaml | ||
| swagger_contract_test.go | ||
README.md
文档已迁至 website-docs
产品、部署、API 和开发文档统一维护在 website-docs。已迁移、重复和过时的旧手写文档已删除;历史内容可从 Git 历史查看。
本目录仅保留以下工程资源及本入口说明:
docs.go、swagger.json、swagger.yaml与契约测试:参与后端编译和测试,生成物仍由make docs更新。LITE.md:Lite 发布包复制为离线 README。images/、assets/:README、Helm 等仍使用的图片资源。poc/docker-sandbox/:独立 Go 实验模块,保留源码和运行说明,不作为当前产品指南。
这些资源尚有编译、发布或历史实验用途,不能直接整目录删除。新的产品说明不要再放入此处。