docs: make Chinese README the default

README.md

@@ -1,3 +1,8 @@
+<!-- WEHUB_ZH_README -->
+> [!NOTE]
+> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。  
+> [English](./README.en.md) · [原始项目](https://github.com/zzet/gortex) · [上游 README](https://github.com/zzet/gortex/blob/HEAD/README.md)  
+> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
 
 <div align="center">
 <p align="center">
@@ -5,9 +10,9 @@
 </p>
 
 
-### High-performance and efficient code-intelligence engine for AI agents and IDE
-#### Indexes code into graph and exposes it via CLI, MCP Server, and web UI. Multi-repository support by default.
-#### Single static binary for macOS, Linux, and Windows — no dependency chain, simple installation and use.
+### 面向 AI 智能体与 IDE 的高性能高效代码智能引擎
+#### 将代码索引为图结构，并通过 CLI、MCP Server 与 Web UI 暴露。默认支持多仓库。
+#### macOS、Linux 与 Windows 单静态二进制 — 无依赖链，安装与使用简单。
 
 ---
 [![CI](https://github.com/zzet/gortex/actions/workflows/ci.yml/badge.svg)](https://github.com/zzet/gortex/actions/workflows/ci.yml)
@@ -25,44 +30,44 @@
   <a href="https://trendshift.io/repositories/36832" target="_blank"><img src="https://trendshift.io/api/badge/repositories/36832" alt="zzet%2Fgortex | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 </div>
 
-High-quality parsing 257 languages/grammars through tree-sitter AST analysis, in-process resolvers, enhanced with [compiler-grade resolution](https://github.com/zzet/gortex/blob/main/docs/lsp.md) for Python, TypeScript / JavaScript, PHP, C#, Go, C, C++, Java, Kotlin, Swift, Zig, Rust, Ruby, Elixir, Ocaml, Haskell, and [others](https://github.com/zzet/gortex/blob/main/docs/languages.md#at-a-glance) - producing a persistent provenance-tiered knowledge graph of functions, classes, call chains, HTTP routes, and cross-service contracts and calls with a strong confidence model. 175 (configurable) MCP tools - use only what you need. Zero dependencies. Plug and play across 18 coding agents. **Up to 50× fewer tokens per response**. Reproducible [benchmarks](BENCHMARK.md).
+通过 tree-sitter AST 分析、进程内解析器，并借助 [编译器级解析](https://github.com/zzet/gortex/blob/main/docs/lsp.md))（适用于 Python、TypeScript / JavaScript、PHP、C#、Go、C、C++、Java、Kotlin、Swift、Zig、Rust、Ruby、Elixir、Ocaml、Haskell 及[其他语言](https://github.com/zzet/gortex/blob/main/docs/languages.md#at-a-glance))），高质量解析 257 种语言/语法，生成函数、类、调用链、HTTP 路由以及跨服务契约与调用的持久化、来源分级知识图谱，并具备强置信度模型。175 个（可配置）MCP 工具 — 按需使用即可。零依赖。即插即用，支持 18 种编程智能体。**每次响应最多可减少 50× token**。可复现的[基准测试](BENCHMARK.md)。
 
 
-> 18 AI coding agents (Claude Code, Kiro, Cursor, Windsurf, VS Code / Copilot, Continue.dev, Cline, OpenCode, Antigravity, Codex CLI, Gemini CLI, Zed, Aider, Kilo Code, OpenClaw, Hermes, Oh My Pi, Pi) supported out of the box.
+> 开箱即用支持 18 种 AI 编程智能体（Claude Code、Kiro、Cursor、Windsurf、VS Code / Copilot、Continue.dev、Cline、OpenCode、Antigravity、Codex CLI、Gemini CLI、Zed、Aider、Kilo Code、OpenClaw、Hermes、Oh My Pi、Pi）。
 >
-> One install configures every one detected on your machine — see [docs/agents.md](docs/agents.md).
+> 一次安装即可配置本机检测到的所有智能体 — 参见 [docs/agents.md](docs/agents.md)。
 
 <details>
-<summary>Gortex Web UI — force-directed knowledge graph visualization</summary>
+<summary>Gortex Web UI — 力导向知识图谱可视化</summary>
 
-![Gortex Web UI — force-directed knowledge graph visualization](assets/graph.png)
+![Gortex Web UI — 力导向知识图谱可视化](assets/graph.png)
 
 </details>
 
-## Why it matters
+## 为何重要
 
-- **50× fewer tokens per response** — graph-native lookups beat naive file reads. Agents read **just what they need**, not the full file, not the 500-line file around it.
-- **Full development cycle** - no 'read file before edit'. Agents ask for sources, tell what to change, and don't waste context of reading noise.
-- **257 languages/grammars** - every file in the repository reachable; no mix of tools and bloating/hallycinating agents. Three tiers (bespoke tree-sitter, regex, forest-backed signatures) plus Jupyter and Databricks notebooks → [docs/languages.md](docs/languages.md)
-- **Cross-repo by default** — N repos in one graph; contracts, references, and call chains span repo boundaries with evidence-gated resolution, contract matching, impact analysis, per-session isolation → [docs/multi-repo.md](docs/multi-repo.md)
-- **Extreamly fast analysis** — a precomputed depth-3 reach index turns blast-radius queries into O(seeds × reach) map lookups. Safe to ask "what breaks if I change this?" on every edit. No dozens of tool calls to grasp context.
-- **Zero external dependencies** — single binary, everything in-process. No network, no model download to get started. Install, start daemon, use.
-- **Agent integrations (17)** — `gortex init` configures every detected coding assistant on the machine → [docs/agents.md](docs/agents.md)
-- **100+ MCP tools, 16 resources, 3 prompts** — symbol lookup, call chains, blast radius, dataflow, clone detection, refactoring, code actions → [docs/mcp.md](docs/mcp.md)
-- **Semantic search default-on** — baked GloVe-50d (3.8 MB embedded), hybrid BM25 + vector + RRF, zero deps; opt-in MiniLM / Ollama / OpenAI → [docs/semantic-search.md](docs/semantic-search.md)
-- **Speculative execution** — `preview_edit` / `simulate_chain` answer "what would change if I applied this WorkspaceEdit?" without touching disk
-- **Live editor overlays** — push unsaved buffers as a shadow graph; tools read through it. Branching for parallel speculative sessions
-- **GCX1 wire format** — published, round-trippable. **An additional −27% tokens vs JSON** at same fidelity → [docs/wire-format.md](docs/wire-format.md)
-- **Long-living daemon** — one process serves every IDE window; live fsnotify, on-disk snapshots, restart, OS-supervised lifecycle
-- **9 LLM providers (optional)** — local llama.cpp, Anthropic, OpenAI, Ollama, Claude / Codex CLI subprocess, Gemini, Bedrock, DeepSeek → [docs/llm.md](docs/llm.md)
-- **Composable safety** — `verify_change`, `check_guards`, `audit_agent_config` flag broken callers, guard violations, stale docs before they ship
-- **PR review, end to end** — `gortex prs` triages open PRs (per-PR blast radius, merge-order conflicts via shared communities, AI-ranked queue, reviewer suggestions); `gortex review` emits line-anchored findings with a BLOCK/REVIEW/APPROVE verdict from a graph-grounded rulepack; MCP tools (`pr_risk`, `get_pr_impact`, `review`, `review_pack`, `post_review`, …) expose it to agents → [docs/cli.md](docs/cli.md)
-- **HTTP server + Web UI** — versioned `/v1/*` API + MCP 2026 Streamable HTTP; standalone Next.js 15 UI with five 3D graph modes → [docs/server.md](docs/server.md)
-- **Telemetry off by default** — opt-in anonymous tool/command counts only (no code, paths, names, or exact counts); nothing transmitted unless you configure an endpoint. `gortex telemetry on|off|status`; honours `DO_NOT_TRACK` → [docs/telemetry.md](docs/telemetry.md)
+- **每次响应减少 50× token** — 基于图谱的原生查询优于朴素的文件读取。智能体只读取**所需内容**，而非整个文件，也不是其周围那 500 行。
+- **完整开发周期** — 无需「先读文件再编辑」。智能体查询源码、说明要改什么，不会因阅读噪音浪费上下文。
+- **257 种语言/语法** — 仓库中每个文件均可触达；无需混用多种工具，避免智能体臃肿与幻觉。三层机制（定制 tree-sitter、正则、forest 支撑签名）外加 Jupyter 与 Databricks 笔记本 → [docs/languages.md](docs/languages.md)
+- **默认跨仓库** — N 个仓库纳入同一图谱；契约、引用与调用链跨越仓库边界，具备证据门控解析、契约匹配、影响分析与会话级隔离 → [docs/multi-repo.md](docs/multi-repo.md)
+- **极速分析** — 预计算的深度 3 可达索引将爆炸半径查询转化为 O(seeds × reach) 的映射查找。每次编辑都可安全地问「若我改这里，什么会坏？」。无需数十次工具调用来把握上下文。
+- **零外部依赖** — 单一二进制，一切在进程内完成。无需网络，无需下载模型即可起步。安装、启动守护进程、使用。
+- **智能体集成（17）** — `gortex init` 为本机检测到的每个编程助手完成配置 → [docs/agents.md](docs/agents.md)
+- **100+ MCP 工具、16 个资源、3 个提示** — 符号查找、调用链、爆炸半径、数据流、克隆检测、重构、代码操作 → [docs/mcp.md](docs/mcp.md)
+- **语义搜索默认开启** — 内置 GloVe-50d（嵌入 3.8 MB），混合 BM25 + 向量 + RRF，零依赖；可选 MiniLM / Ollama / OpenAI → [docs/semantic-search.md](docs/semantic-search.md)
+- **推测执行** — `preview_edit` / `simulate_chain` 在不触碰磁盘的情况下回答「若我应用此 WorkspaceEdit，会发生什么变化？」
+- **实时编辑器叠加层** — 将未保存缓冲区推送为影子图谱；工具透过它读取。支持并行推测会话的分支
+- **GCX1 线格式** — 已发布、可往返。相同保真度下**比 JSON 再少 27% token** → [docs/wire-format.md](docs/wire-format.md)
+- **长驻守护进程** — 单一进程服务所有 IDE 窗口；实时 fsnotify、磁盘快照、重启、操作系统监管生命周期
+- **9 个 LLM 提供商（可选）** — 本地 llama.cpp、Anthropic、OpenAI、Ollama、Claude / Codex CLI 子进程、Gemini、Bedrock、DeepSeek → [docs/llm.md](docs/llm.md)
+- **可组合安全** — `verify_change`、`check_guards`、`audit_agent_config` 在问题上线前标记损坏的调用方、守卫违规与过时文档
+- **PR 审查，端到端** — `gortex prs` 对开放 PR 进行分诊（按 PR 的爆炸半径、通过共享社区检测合并顺序冲突、AI 排序队列、审查者建议）；`gortex review` 输出锚定到行的发现，并给出基于图谱规则包的 BLOCK/REVIEW/APPROVE 裁决；MCP 工具（`pr_risk`、`get_pr_impact`、`review`、`review_pack`、`post_review`、…）向智能体暴露上述能力 → [docs/cli.md](docs/cli.md)
+- **HTTP 服务器 + Web UI** — 版本化 `/v1/*` API + MCP 2026 Streamable HTTP；独立 Next.js 15 UI，含五种 3D 图谱模式 → [docs/server.md](docs/server.md)
+- **遥测默认关闭** — 仅可选匿名工具/命令计数（不含代码、路径、名称或精确计数）；除非你配置端点，否则不传输任何数据。`gortex telemetry on|off|status`；遵循 `DO_NOT_TRACK` → [docs/telemetry.md](docs/telemetry.md)
 
-Full catalog of features: [docs/features.md](docs/features.md). Complete CLI reference: [docs/cli.md](docs/cli.md).
+完整功能目录：[docs/features.md](docs/features.md)。完整 CLI 参考：[docs/cli.md](docs/cli.md)。
 
-## Install
+## 安装
 
 ```bash
 # macOS / Linux
@@ -72,9 +77,9 @@ curl -fsSL https://get.gortex.dev | sh
 irm https://get.gortex.dev/install.ps1 | iex
 ```
 
-Detects OS/arch, verifies SHA256 + cosign, installs to PATH. Re-run to upgrade. Homebrew, `.deb` / `.rpm` / `.apk`, scoop, signed binaries, and from-source builds: [docs/installation.md](docs/installation.md).
+检测 OS/架构，校验 SHA256 + cosign，安装到 PATH。重新运行即可升级。Homebrew、`.deb` / `.rpm` / `.apk`、scoop、签名二进制及源码构建：[docs/installation.md](docs/installation.md)。
 
-## Quick Start
+## 快速开始
 
 ```bash
 gortex install                          # one-time machine setup (MCP, skills, slash commands)
@@ -83,40 +88,40 @@ gortex track ~/projects/myapp           # add a repo
 cd ~/projects/myapp && gortex init      # per-repo: .mcp.json, hooks, community routing
 ```
 
-Your AI assistant now uses graph queries. Full 15-minute walkthrough: [docs/onboarding.md](docs/onboarding.md).
+你的 AI 助手现已使用图谱查询。完整 15 分钟入门：[docs/onboarding.md](docs/onboarding.md)。
 
-## Cross-Repo API Contracts
+## 跨仓库 API 契约
 
-Gortex auto-detects API contracts across repos and matches providers to consumers, surfaced via the `contracts` MCP tool and the web UI Contracts page.
+Gortex 自动检测跨仓库 API 契约并将提供方与消费者匹配，通过 `contracts` MCP 工具及 Web UI 契约页面呈现。
 
-| Contract type | Detection | Provider | Consumer |
+| 契约类型 | 检测方式 | 提供方 | 消费方 |
 |--------------|-----------|----------|----------|
-| **HTTP routes** | Framework annotations (gin, Express, FastAPI, Spring, …) | Route handler | HTTP client calls (`fetch`, `http.Get`) |
-| **gRPC** | Proto service definitions | Service RPC | Client stub calls |
-| **GraphQL** | Schema type/field definitions | Schema | Query/mutation strings |
-| **Message topics** | Kafka / RabbitMQ / NATS / Redis pub/sub | Publish calls | Subscribe calls |
-| **WebSocket** | Event emit/listen patterns | `emit()` | `on()` |
-| **Env vars** | `os.Getenv`, `process.env`, `.env` files | `Setenv` / `.env` | `Getenv` / `process.env` |
-| **OpenAPI** | Swagger / OpenAPI spec files | Spec paths | (linked to HTTP routes) |
-| **Temporal workflows** | Go / Java SDK annotations | Activity / workflow function | `ExecuteActivity` / `ExecuteChildWorkflow` |
+| **HTTP 路由** | 框架注解（gin、Express、FastAPI、Spring、…） | 路由处理器 | HTTP 客户端调用（`fetch`、`http.Get`） |
+| **gRPC** | Proto 服务定义 | 服务 RPC | 客户端桩调用 |
+| **GraphQL** | Schema 类型/字段定义 | Schema | 查询/变更字符串 |
+| **消息主题** | Kafka / RabbitMQ / NATS / Redis pub/sub | 发布调用 | 订阅调用 |
+| **WebSocket** | 事件 emit/listen 模式 | `emit()` | `on()` |
+| **环境变量** | `os.Getenv`、`process.env`、`.env` 文件 | `Setenv` / `.env` | `Getenv` / `process.env` |
+| **OpenAPI** | Swagger / OpenAPI 规范文件 | 规范路径 | （关联至 HTTP 路由） |
+| **Temporal 工作流** | Go / Java SDK 注解 | Activity / 工作流函数 | `ExecuteActivity` / `ExecuteChildWorkflow` |
 
-Contracts are normalised to canonical IDs (e.g. `http::GET::/api/users/{id}`) and matched across repos to detect orphan providers / consumers and mismatches. See [docs/contracts.md](docs/contracts.md).
+合约（Contracts）会被规范化为规范 ID（canonical IDs，例如 `http::GET::/api/users/{id}`），并在各仓库之间进行匹配，以检测孤立的提供方（providers）/ 消费方（consumers）和不一致项。详见 [docs/contracts.md](docs/contracts.md)。
 
-## Scale — battle-tested on large repos
+## 规模 — 在大型仓库上久经考验
 
-Measured on an Apple Silicon laptop with the default CGO build.
+在 Apple Silicon 笔记本电脑上使用默认 CGO 构建测得。
 
-| Repository | Files | Nodes | Edges | Index time | Throughput | Peak heap |
+| 仓库 | 文件数 | 节点数 | 边数 | 索引时间 | 吞吐量 | 峰值堆内存 |
 | ---------- | ----: | ----: | ----: | ---------: | ---------: | --------: |
 | [torvalds/linux](https://github.com/torvalds/linux) | 70,333 | 1,690,174 | 6,239,570 | ~3 min | 300 files/s | 5.07 GB |
 | [microsoft/vscode](https://github.com/microsoft/vscode) | 10,762 | 204,501 | 808,902 | ~1 min | 143 files/s | 580 MB |
 | zzet/gortex (self) | 430 | 5,583 | 53,830 | 3.4s | 127 files/s | 52 MB |
 
-Parsing dominates wall time (65–80 %); reference resolution and search-index build scale sub-linearly.
+解析占用了绝大部分墙上时钟时间（wall time，65–80%）；引用解析与搜索索引构建的扩展呈次线性（sub-linear）。
 
-## Token savings dashboard
+## Token 节省仪表盘
 
-`gortex savings` reports tokens saved vs naive file reads — per-call, per-session, and cumulative across restarts, priced in USD against the headline model.
+`gortex savings` 会报告相较朴素文件读取（naive file reads）所节省的 token——按每次调用、按会话，以及跨重启的累计值，并按头条模型（headline model）以美元计价。
 
 ```text
 Gortex Token Savings
@@ -128,9 +133,9 @@ Last 7 days ██████████░░░░░░   62.5%  saved 60,1
 All time    ███████████████░   93.3%  saved 11,246,094 / 12,050,716 tokens  $168.69
 ```
 
-`--verbose` adds the per-tool breakdown; `--json` is machine-readable. Full reference: [docs/savings.md](docs/savings.md).
+`--verbose` 提供按工具（per-tool）的细分；`--json` 为机器可读格式。完整参考：[docs/savings.md](docs/savings.md)。
 
-## Architecture
+## 架构
 
 ```
 gortex binary
@@ -143,34 +148,34 @@ gortex binary
                   Persistence     ──> gob+gzip snapshot (pluggable backend)
 ```
 
-Data flow, graph schema (node and edge kinds, multi-repo fields, test taxonomy), persistence model: [docs/architecture.md](docs/architecture.md).
+数据流、图模式（graph schema，节点与边类型、多仓库字段、测试分类法）以及持久化模型：[docs/architecture.md](docs/architecture.md)。
 
-## Documentation
+## 文档
 
-| Topic | Reference |
+| 主题 | 参考 |
 | --- | --- |
-| First-time walkthrough | [onboarding.md](docs/onboarding.md) |
-| Installation & supply-chain verification | [installation.md](docs/installation.md) |
-| Full feature catalog | [features.md](docs/features.md) |
-| CLI reference | [cli.md](docs/cli.md) |
-| MCP tools, resources, prompts | [mcp.md](docs/mcp.md) |
-| Multi-repo workspaces | [multi-repo.md](docs/multi-repo.md) |
-| HTTP server + Web UI + MCP 2026 transport | [server.md](docs/server.md) |
-| Cross-repo API contracts | [contracts.md](docs/contracts.md) |
-| Semantic search | [semantic-search.md](docs/semantic-search.md) |
-| Optional LLM features | [llm.md](docs/llm.md) |
-| LSP integration | [lsp.md](docs/lsp.md) |
-| Per-community skills & agent usage | [skills.md](docs/skills.md) |
-| AI agent adapters (17) | [agents.md](docs/agents.md) |
-| Supported languages (257) | [languages.md](docs/languages.md) |
-| Token savings | [savings.md](docs/savings.md) |
-| GCX1 wire format | [wire-format.md](docs/wire-format.md) |
-| Architecture & graph schema | [architecture.md](docs/architecture.md) |
-| Evaluation methodology | [04-evaluation/](docs/04-evaluation/) |
-| Telemetry & privacy | [telemetry.md](docs/telemetry.md) |
-| Versioning policy | [versioning.md](docs/versioning.md) |
+| 首次使用 walkthrough | [onboarding.md](docs/onboarding.md) |
+| 安装与供应链验证 | [installation.md](docs/installation.md) |
+| 完整功能目录 | [features.md](docs/features.md) |
+| CLI 参考 | [cli.md](docs/cli.md) |
+| MCP 工具、资源与提示词 | [mcp.md](docs/mcp.md) |
+| 多仓库工作区 | [multi-repo.md](docs/multi-repo.md) |
+| HTTP 服务器 + Web UI + MCP 2026 传输层 | [server.md](docs/server.md) |
+| 跨仓库 API 合约 | [contracts.md](docs/contracts.md) |
+| 语义搜索 | [semantic-search.md](docs/semantic-search.md) |
+| 可选 LLM 功能 | [llm.md](docs/llm.md) |
+| LSP 集成 | [lsp.md](docs/lsp.md) |
+| 各社区技能与 agent 用法 | [skills.md](docs/skills.md) |
+| AI agent 适配器（17） | [agents.md](docs/agents.md) |
+| 支持的语言（257） | [languages.md](docs/languages.md) |
+| Token 节省 | [savings.md](docs/savings.md) |
+| GCX1 线格式（wire format） | [wire-format.md](docs/wire-format.md) |
+| 架构与图模式 | [architecture.md](docs/architecture.md) |
+| 评估方法论 | [04-evaluation/](docs/04-evaluation/) |
+| 遥测与隐私 | [telemetry.md](docs/telemetry.md) |
+| 版本策略 | [versioning.md](docs/versioning.md) |
 
-## Building from source
+## 从源码构建
 
 ```bash
 make build          # binary with version stamping
@@ -178,12 +183,12 @@ make test           # go test -race ./...
 make lint           # golangci-lint
 ```
 
-Requires Go 1.26+ and CGO (for tree-sitter C bindings).
+需要 Go 1.26+ 与 CGO（用于 tree-sitter C 绑定）。
 
-## License
+## 许可证
 
-Apache License 2.0. See [LICENSE.md](LICENSE.md). Copyright 2024-2026 Andrey Kumanyaev <me@zzet.org>.
+Apache License 2.0。详见 [LICENSE.md](LICENSE.md)。Copyright 2024-2026 Andrey Kumanyaev <me@zzet.org>。
 
-## Contributing
+## 贡献
 
-See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on adding features, language extractors, and submitting PRs.
+有关添加功能、语言提取器（language extractors）以及提交 PR 的指南，请参见 [CONTRIBUTING.md](CONTRIBUTING.md)。