lpeixin/dsh-project-compass ↗★ 2
dsh-project-compass
DeepSeek Harness bundle: 项目罗盘 / Project Compass — 读取现有项目、解析多语言代码、构建统一 IR 与依赖知识图谱,生成带证据引用的上手报告(ONBOARDING / ARCHITECTURE / MODULE_MAP / KEY_FLOWS / GETTING_STARTED),并提供项目级带引用问答。 适合需要快速熟悉新项目、解析多语言代码并构建依赖图谱的开发者。
インストール
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lpeixin/dsh-project-compassドキュメント
README 全文を読む ↗Configuration
Configuration lives in the profile's cordis.patch.yml, addressed by the id project-compass:
- id: project-compass
name: dsh-project-compass
config:
outputDir: docs/project-compass
concurrency: 8
budget:
maxFiles: 20000
maxFileBytes: 262144
maxTotalBytes: 67108864
maxDurationMs: 600000
maxChunks: 20000
ignore: []
include: []
sensitive:
extraPatterns: []
llm:
enabled: false
contextInjection: false
| Key | Default | Effect |
|---|---|---|
outputDir | docs/project-compass | Output directory for the human artifacts (relative to the project root) |
concurrency | 8 | Parse concurrency; raise it for IO-bound workloads, lower it on spinning disks or when there are many very large files |
budget.* | see above | Caps on file count / per-file bytes / total bytes / duration / chunk count; exceeding them truncates and tags the result |
ignore / include | [] | Additional ignore rules (.gitignore syntax, ! negation supported) and force-include rules |
sensitive.extraPatterns | [] | Additional sensitive-file patterns; matching paths are registered only and their contents are never read |
llm.enabled | false | Whether the LLM may be called to generate narrative (does not change retrieval or fact extraction) |
contextInjection | false | Whether to inject a project brief into the agent's system prompt |
Per-key details, matching semantics, the default sensitive-file list, tuning for large repos / monorepos and the LLM privacy notes are in docs/CONFIG.md.
Project-level configuration (letting a repository carry its own preferences) is out of scope for this version; see docs/ROADMAP.md.