dsh-code-index

English | 中文

Semantic repo index — a DeepSeek Harness (dsh) plugin that gives the agent a codebase map: a tree-sitter symbol index, ranked symbol search, and a bounded auto-updating repo map in the system prompt.

Fills a real ecosystem gap: search of the dsh-plugin topic (2026-08) shows git/voice/browser/memory plugins galore, but no native, model-usable code index / repo-map capability — the kind of thing aider's repo-map and Cursor's @Codebase do for their agents.

What the model gets

Plus an optional auto-injected system prompt section (code-index:repo-map, order 60): a compact ranked map of the default workspace, refreshed with a 60s TTL. Set autoInject: false to disable and rely on the code_map tool only.

Install

Requires dsh (any install path — npx, npm, or source) and Node ≥ 22.

# from npm (prebuilt)
npx @deepseek-ai/dsh plugin --profile web add dsh-code-index

# or from a directory containing this checkout
npx @deepseek-ai/dsh plugin --profile web add ./dsh-code-index

Restart the Web UI (npx @deepseek-ai/dsh web) — startup logs confirm each tool:

[dsh-code-index] plugin loaded
[dsh-code-index] registered tool: code_index
...

Verify the composed config without booting: dsh --profile web --dump-config.

Using it

In a workspace session, ask the agent:

• "Which repo are we in — run code_map first."
• "Find every function whose name contains parse and where it lives."
• "List the exported symbols in src/core."
• "Rebuild the code index."

No API key is needed to index; the model must of course be configured to call the tools.

Example (input → output)

User prompt:

Which repo are we in? Run code_map first, then find where extractSymbols is defined.

The agent calls the tools in turn:

code_map
# repo map
## src/extract.ts (14)
  function extractSymbols(code, id) :121
  function languageForFile(filePath) :37
  ...

code_search { query: "extractSymbols" }
export function extractSymbols(code, id) — src/extract.ts:121

The index builds lazily on first use; later calls are served from the on-disk cache with mtime-incremental refresh.

Configuration

Options are passed as the plugin row's config in the profile patch (or defaults are used if absent):

# $DSH_HOME/profiles/<name>/cordis.patch.yml — a bare row overrides by id.
- id: code-index
  config:
    excludeDirs: [generated, playground]
    mapTopFiles: 30
    mapMaxChars: 4000
    autoInject: true

Supported languages

TypeScript + JavaScript + Python (.ts .tsx .mts .cts .js .jsx .mjs .cjs .py .pyi) via tree-sitter WASM — pure parsing, no native build. The symbol provider seam (src/extract.ts + grammars) is where other languages/embeddings plug in later.

How it works

• Index build (src/buildIndex.ts): recursive scan (excludes applied), per-file tree-sitter extraction (src/extract.ts), JSON cache under <repo>/.dsh-code-index/, incremental refresh by mtime (only touched files re-parse).
• Search (src/search.ts): pure scoring — exact 1 / prefix 0.8 / substring 0.5, export boost, name order tiebreak.
• Repo map (src/repomap.ts): density-aware file score (class/interface/function weighted, mild anti-bloat), top-N files, per-file symbol cap, hard char truncation.
• Workspace resolution: each tool resolves the session cwd (agent.session.header.cwd) and walks up to the nearest .git (bounded — a directory without a repo marker is never indexed).

Known limitations

• web-tree-sitter pinned to ^0.20.8 — newer releases expect dylinked grammar wasm while tree-sitter-wasms ships static builds; this pair is verified working under Node ≥ 22/24.
• Auto-injected section targets the default workspace (launch directory, matching headless/CLI mode). Multi-workspace Web UI sessions should use code_map/code_symbols (they resolve per-session cwd).
• Local variables are indexed too — recall over precision; code_search ranking keeps them low.
• Developer-preview harness: expect breaking harness/plugin API changes upstream.

Development

pnpm install
pnpm test        # vitest — extractor, scan, cache, search, repo map (35 tests)
pnpm typecheck
pnpm build       # tsup → dist/index.js (ESM, external deps)

License

MIT. Not affiliated with DeepSeek; built on the public dsh plugin surface.