RepoNova

  Your Codebase                      /reponova-enrich                             AI Agent
  ─────────────                      ────────────────                             ────────

  Source Code          ──────────►   1. tree-sitter AST parsing                   graph_search
  Markdown / Docs                    2. Symbol + edge extraction        ──────►   graph_impact
  Diagrams (plugins)                 3. Louvain communities                       graph_path
  Multi-repo                         4. Enrichment (summaries + descriptions)     graph_similar
                                     5. TF-IDF / ONNX / API embeddings
                                     6. HTML visualizations                       ... (11 tools)

reponova install --target opencode

reponova lang suggest

You: "What would be the impact of refactoring the authenticate function?"
Agent: [calls graph_impact] → shows upstream/downstream blast radius across repos

You: /reponova-enrich
Agent: [builds structural graph]
       [reads input batches, reasons about architecture, writes output batches]
       [CLI merges results, applies mutations]
       [runs downstream phases: search index, embeddings, HTML]

reponova install --target <editor> [--graph <path>]

reponova build [--config <path>] [--force] [--target <phase,...>] [--start-after <phase>] [--check <phase>]

Level 0: file-detection
Level 1: graph, outlines                         (parallel)
Level 2: communities
Level 3: enrich
Level 4: search-index, embeddings, html, report  (parallel)

reponova enrich [--config <path>]

reponova enrich:metrics                        # Step 0: candidates + edge density
reponova enrich:prepare <step>                 # Prepare input batches
reponova enrich:merge <step>                   # Merge output batches
reponova enrich:apply                          # Step 5: apply routing + restructure
reponova enrich:finalize                       # Step 7: produce final output files

reponova mcp [--graph <path>]

reponova check [--config <path>] [--graph <path>]

reponova lang <subcommand> [args] [flags]

reponova cache --status                        # Show cache status for all phases
reponova cache --check <phase>                 # Check if fresh (exit 0 = fresh, exit 1 = stale)
reponova cache --seal <phase>                  # Manually seal (marks as up-to-date)
reponova cache --invalidate <phase>            # Invalidate (forces re-run on next build)

reponova models <subcommand>

reponova lang suggest                         # scan repos + propose plugins (interactive)
reponova lang add @reponova/lang-python
reponova lang add @reponova/lang-typescript
reponova lang add @reponova/lang-tsx
reponova lang add @exampleorg/lang-rust       # community plugins work too
reponova lang list                            # show declared plugins
reponova lang remove svg                      # uninstall by plugin id

# ──────────────────────────────────────────────────────────────────────────────
# reponova.yml — Full Configuration Reference
# ──────────────────────────────────────────────────────────────────────────────

# Where to write build output
# Default: "reponova-out"
output: ../reponova-out

# ── Repositories ──────────────────────────────────────────────────────────────
repos:
  - name: api-service           # unique identifier
    path: ../services/api       # path relative to this file
  - name: core-lib
    path: ../services/core

# ── Providers (optional — AI backends) ────────────────────────────────────────
# Default (no provider) = fully algorithmic. No downloads, no API keys.
providers:
  my-openai:
    type: openai                  # "openai" | "llama-cpp" | "onnx"
    base_url: https://api.openai.com/v1
    model: text-embedding-3-small
    api_key: ${OPENAI_API_KEY}    # env var (resolved at runtime)
    timeout: 30                   # seconds (default: 30)
  local-llm:
    type: llama-cpp
    model: "hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_M"
    context_size: 512
  local-embeddings:
    type: onnx
    model: all-MiniLM-L6-v2
  ollama:
    type: openai
    base_url: http://localhost:11434/v1
    model: nomic-embed-text

# ── Model Management ─────────────────────────────────────────────────────────
models:
  cache_dir: ~/.cache/reponova/models   # default
  gpu: auto                             # "auto" | "cpu" | "cuda" | "metal" | "vulkan"
  threads: 0                            # 0 = auto-detect
  download_on_first_use: true

# ── Source Code Filters ───────────────────────────────────────────────────────
patterns: []                    # empty = auto-detect by extension
exclude: []                     # e.g. ["**/generated/**", "**/*.test.ts"]
exclude_common: true            # skip node_modules, __pycache__, .git, venv, dist, build, ...
incremental: true               # SHA256 file hashing — only re-parse changed files

# ── Documentation ─────────────────────────────────────────────────────────────
docs:
  enabled: true
  patterns: []                  # empty = auto-detect (.md, .txt, .rst)
  exclude: []
  max_file_size_kb: 500

# ── Language Plugins ──────────────────────────────────────────────────────────
# Declare plugins here. Installed via `reponova lang add <package>`.
# If `package` is omitted, resolved as @reponova/lang-<key>.
plugins:
  python:                          # shorthand → @reponova/lang-python
    enabled: true
  rust:                            # community plugin → explicit package
    package: "@exampleorg/lang-rust"
    enabled: true
  plantuml:
    enabled: true
    parse: true                    # plugin-specific option

# ── Embeddings ────────────────────────────────────────────────────────────────
# Default: TF-IDF (fast, no download). Set provider for ONNX or remote embeddings.
embeddings:
  enabled: true
  provider: my-openai              # enables llm embeddings
  batch_size: 128

# ── Enrich ────────────────────────────────────────────────────────────────────
# Default (no provider): algorithmic (rule-based summaries + descriptions)
# With provider: intelligent multi-step LLM enrichment pipeline
enrich:
  enabled: true
  provider: local-llm             # enables intelligent enrichment
  threshold: 0.8                  # top 20% of nodes by degree get descriptions
  max_communities: 0              # 0 = no limit
  candidate_threshold: 0.3        # boundary ratio for routing candidates
  description_batch_tokens: 40000 # token budget per description batch
  routing_batch_size: 30
  concurrency: 4                  # max parallel LLM calls
  max_retry_depth: 3
  max_tokens:                     # per-step LLM output token limits
    descriptions: 32768
    profiles: 2048
    routing: 8192
    restructure: 4096
  profile:                        # community profile prompt limits
    max_nodes: 80
    max_edges: 50
  restructure_max_pairs: 20       # max cross-community pairs for merge/split analysis

# ── HTML ──────────────────────────────────────────────────────────────────────
html: true
# html_min_degree: 3

# ── Outlines ──────────────────────────────────────────────────────────────────
outlines:
  enabled: true

# ── Server ────────────────────────────────────────────────────────────────────
server: {}

output: ../reponova-out
repos:
  - name: my-project
    path: ..

output: ../reponova-out
repos:
  - name: api
    path: ../services/api
  - name: core
    path: ../services/core

output: ../reponova-out
repos:
  - name: my-project
    path: ..
providers:
  local-llm:
    type: openai
    base_url: http://localhost:11434/v1
    model: llama3.2
enrich:
  provider: local-llm

reponova-out/
├── graph.json                    # Full graph: nodes, edges, community assignments
├── graph-enriched.json           # Enriched graph (after intelligent enrichment)
├── graph-nodes.json              # Intermediate (pre-community detection)
├── detected-files.json           # Detected file list
├── graph.html                    # Interactive visualization (vis.js)
├── graph_communities.html        # Community-focused visualization
├── graph_search.db               # SQLite search index
├── report.md                     # Build report: stats, hotspots, communities
├── community_summaries.json      # Community summaries
├── node_descriptions.json        # Node descriptions
├── tfidf_idf.json                # TF-IDF vocabulary weights
├── vectors/                      # LanceDB vector store
├── outlines/                     # Code outlines per file
├── .enrich/                      # Enrichment intermediates (intelligent mode)
│   ├── candidates.json           #   boundary node classification
│   ├── edge-density.json         #   inter-community density
│   ├── descriptions.json         #   merged descriptions
│   ├── profiles.json             #   merged community profiles
│   ├── routing.json              #   merged routing decisions
│   ├── restructure.json          #   merge/split proposals
│   ├── graph-applied.json        #   graph after mutations
│   └── updated-profiles.json     #   re-profiled communities
└── .cache/                       # Incremental build cache

import { build } from "reponova";

const result = await build("./reponova.yml");
// result.outputDir, result.phases, result.totalProcessed

import { build, registerExtractor, registerOutlineLanguage } from "reponova";
import type { LanguageExtractor, LanguageSupport } from "reponova";

registerExtractor(myExtractor);
registerOutlineLanguage("rust", ["rs"], myOutline);
const result = await build("./reponova.yml");

import {
  openDatabase, initializeSchema, populateDatabase,
  loadGraphData, searchNodes, analyzeImpact, findShortestPath,
} from "reponova";

const graphData = loadGraphData("./reponova-out/graph.json");
const db = await openDatabase(":memory:");
initializeSchema(db);
populateDatabase(db, graphData);

const results = searchNodes(db, "authentication", { top_k: 5, type: "function" });
const impact = analyzeImpact(db, "Function:authenticate_user", { max_depth: 3 });
const path = findShortestPath(db, graphData, "ModuleA", "ModuleB");

import { ContextBuilder, loadConfig } from "reponova";

const { config } = loadConfig("./reponova.yml");
const builder = new ContextBuilder(db, graphData, "./reponova-out");
await builder.initialize(config.embeddings);
const context = await builder.buildContext({ query: "authentication flow", maxTokens: 4000 });

reponova lang add @exampleorg/lang-rust

plugins:
  rust:
    package: "@exampleorg/lang-rust"
    enabled: true

interface LanguagePlugin {
  readonly id: string;              // e.g. "python", "plantuml"
  readonly fileType?: string;       // category label in detected-files.json (default: id)
  readonly grammarPath?: string;    // absolute path to tree-sitter WASM grammar
  readonly extractor: LanguageExtractor;
  readonly outline?: LanguageSupport;
  readonly configDefaults?: Record<string, unknown>;  // default plugin config values
}

interface LanguageExtractor {
  readonly languageId: string;
  readonly wasmFile?: string;
  extract(
    tree: SyntaxTree | null,
    sourceCode: string,
    filePath: string,
    pluginConfig?: Readonly<Record<string, unknown>>,
  ): FileExtraction;
  resolveImportPath(importModule: string, currentFilePath: string): string[];
}

interface FileExtraction {
  filePath: string;
  language: string;
  symbols: SymbolNode[];
  imports: ImportDeclaration[];
  references: SymbolReference[];
}

import type { LanguagePlugin } from "reponova";
import { PythonExtractor } from "./extractor.js";
import { python as pythonOutline } from "./outline.js";
import { resolve } from "node:path";
import { fileURLToPath } from "node:url";

const grammarPath = resolve(fileURLToPath(new URL(".", import.meta.url)), "../grammars/tree-sitter-python.wasm");

export const plugin: LanguagePlugin = {
  id: "python",
  fileType: "python",
  grammarPath,
  extractor: new PythonExtractor(),
  outline: pythonOutline,
};

import type { LanguagePlugin } from "reponova";
import { RustExtractor } from "./extractor.js";

export const plugin: LanguagePlugin = {
  id: "rust",
  fileType: "rust",
  extractor: new RustExtractor(),
};

{
  "name": "@exampleorg/lang-rust",
  "version": "1.0.0",
  "type": "module",
  "exports": { ".": "./dist/index.js" },
  "keywords": ["reponova-language"],
  "peerDependencies": { "reponova": ">=0.5.0" },
  "reponova": {
    "type": "language",
    "extensions": [".rs"]
  }
}

plugins:
  rust:
    package: "@exampleorg/lang-rust"
    enabled: true
    exclude: ["**/target/**"]

plugins:
  python:
    enabled: true       # resolves to @reponova/lang-python

interface LanguageSupport {
  readonly wasmFile: string;
  treeSitterExtract(
    rootNode: SyntaxNode,
    filePath: string,
    lineCount: number,
    pluginConfig?: Readonly<Record<string, unknown>>,
  ): FileOutline;
  regexExtract(
    filePath: string,
    source: string,
    lineCount: number,
    pluginConfig?: Readonly<Record<string, unknown>>,
  ): FileOutline;
}