@zuvia-software-solutions/code-mapper 1.4.0

package/dist/config/ignore-service.js

@@ -0,0 +1,282 @@
+// code-mapper/src/config/ignore-service.ts
+/** @file ignore-service.ts @description Hardcoded and user-configurable ignore rules for file/directory filtering during repo traversal */
+import ignore from 'ignore';
+import fs from 'fs/promises';
+import nodePath from 'path';
+const DEFAULT_IGNORE_LIST = new Set([
+    // Version control
+    '.git',
+    '.svn',
+    '.hg',
+    '.bzr',
+    // IDEs and editors
+    '.idea',
+    '.vscode',
+    '.vs',
+    '.eclipse',
+    '.settings',
+    '.DS_Store',
+    'Thumbs.db',
+    // Dependencies
+    'node_modules',
+    'bower_components',
+    'jspm_packages',
+    'vendor', // PHP/Go
+    // 'packages' not ignored — commonly used for monorepo source code
+    'venv',
+    '.venv',
+    'env',
+    '.env',
+    '__pycache__',
+    '.pytest_cache',
+    '.mypy_cache',
+    'site-packages',
+    '.tox',
+    'eggs',
+    '.eggs',
+    'lib64',
+    'parts',
+    'sdist',
+    'wheels',
+    // Build outputs
+    'dist',
+    'build',
+    'out',
+    'output',
+    'bin',
+    'obj',
+    'target', // Java, Rust
+    '.next',
+    '.nuxt',
+    '.output',
+    '.vercel',
+    '.netlify',
+    '.serverless',
+    '_build',
+    'public/build',
+    '.parcel-cache',
+    '.turbo',
+    '.svelte-kit',
+    // Test and coverage
+    'coverage',
+    '.nyc_output',
+    'htmlcov',
+    '.coverage',
+    '__tests__',
+    '__mocks__',
+    '.jest',
+    // Logs and temp
+    'logs',
+    'log',
+    'tmp',
+    'temp',
+    'cache',
+    '.cache',
+    '.tmp',
+    '.temp',
+    // Generated and compiled
+    '.generated',
+    'generated',
+    'auto-generated',
+    '.terraform',
+    '.serverless',
+    // Misc
+    '.husky',
+    '.github',
+    '.circleci',
+    '.gitlab',
+    'fixtures',
+    'snapshots',
+    '__snapshots__',
+]);
+const IGNORED_EXTENSIONS = new Set([
+    // Images
+    '.png', '.jpg', '.jpeg', '.gif', '.svg', '.ico', '.webp', '.bmp', '.tiff', '.tif',
+    '.psd', '.ai', '.sketch', '.fig', '.xd',
+    // Archives
+    '.zip', '.tar', '.gz', '.rar', '.7z', '.bz2', '.xz', '.tgz',
+    // Binary and compiled
+    '.exe', '.dll', '.so', '.dylib', '.a', '.lib', '.o', '.obj',
+    '.class', '.jar', '.war', '.ear',
+    '.pyc', '.pyo', '.pyd',
+    '.beam',
+    '.wasm',
+    '.node',
+    // Documents
+    '.pdf', '.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx',
+    '.odt', '.ods', '.odp',
+    // Media
+    '.mp4', '.mp3', '.wav', '.mov', '.avi', '.mkv', '.flv', '.wmv',
+    '.ogg', '.webm', '.flac', '.aac', '.m4a',
+    // Fonts
+    '.woff', '.woff2', '.ttf', '.eot', '.otf',
+    // Databases
+    '.db', '.sqlite', '.sqlite3', '.mdb', '.accdb',
+    // Minified and bundled
+    '.min.js', '.min.css', '.bundle.js', '.chunk.js',
+    // Source maps
+    '.map',
+    // Lock files
+    '.lock',
+    // Certificates and keys
+    '.pem', '.key', '.crt', '.cer', '.p12', '.pfx',
+    // Data files
+    '.csv', '.tsv', '.parquet', '.avro', '.feather',
+    '.npy', '.npz', '.pkl', '.pickle', '.h5', '.hdf5',
+    // Misc
+    '.bin', '.dat', '.data', '.raw',
+    '.iso', '.img', '.dmg',
+]);
+// Exact filenames to ignore
+const IGNORED_FILES = new Set([
+    'package-lock.json',
+    'yarn.lock',
+    'pnpm-lock.yaml',
+    'composer.lock',
+    'Gemfile.lock',
+    'poetry.lock',
+    'Cargo.lock',
+    'go.sum',
+    '.gitignore',
+    '.gitattributes',
+    '.npmrc',
+    '.yarnrc',
+    '.editorconfig',
+    '.prettierrc',
+    '.prettierignore',
+    '.eslintignore',
+    '.dockerignore',
+    'Thumbs.db',
+    '.DS_Store',
+    'LICENSE',
+    'LICENSE.md',
+    'LICENSE.txt',
+    'CHANGELOG.md',
+    'CHANGELOG',
+    'CONTRIBUTING.md',
+    'CODE_OF_CONDUCT.md',
+    'SECURITY.md',
+    '.env',
+    '.env.local',
+    '.env.development',
+    '.env.production',
+    '.env.test',
+    '.env.example',
+]);
+// NOTE: Negation patterns in .code-mapperignore (e.g. `!vendor/`) cannot override
+// DEFAULT_IGNORE_LIST entries — hardcoded list protects against indexing dirs that
+// are almost never source code. To include such dirs, remove them from the list
+/**
+ * Check whether a file path should be ignored based on hardcoded rules
+ * @param filePath - Relative or absolute file path to check
+ * @returns true if the path matches any ignore rule
+ */
+export const shouldIgnorePath = (filePath) => {
+    const normalizedPath = filePath.replace(/\\/g, '/');
+    const parts = normalizedPath.split('/');
+    const fileName = parts[parts.length - 1];
+    const fileNameLower = fileName.toLowerCase();
+    // Check if any path segment matches the ignore list
+    for (const part of parts) {
+        if (DEFAULT_IGNORE_LIST.has(part)) {
+            return true;
+        }
+    }
+    // Check exact filename
+    if (IGNORED_FILES.has(fileName) || IGNORED_FILES.has(fileNameLower)) {
+        return true;
+    }
+    // Check extension
+    const lastDotIndex = fileNameLower.lastIndexOf('.');
+    if (lastDotIndex !== -1) {
+        const ext = fileNameLower.substring(lastDotIndex);
+        if (IGNORED_EXTENSIONS.has(ext))
+            return true;
+        // Handle compound extensions (e.g. .min.js, .bundle.js)
+        const secondLastDot = fileNameLower.lastIndexOf('.', lastDotIndex - 1);
+        if (secondLastDot !== -1) {
+            const compoundExt = fileNameLower.substring(secondLastDot);
+            if (IGNORED_EXTENSIONS.has(compoundExt))
+                return true;
+        }
+    }
+    // TODO: dot-file filtering intentionally skipped — many are important configs
+    // Relies on explicit IGNORED_FILES list above instead
+    // Ignore generated/bundled code and TypeScript declaration files
+    if (fileNameLower.includes('.bundle.') ||
+        fileNameLower.includes('.chunk.') ||
+        fileNameLower.includes('.generated.') ||
+        fileNameLower.endsWith('.d.ts')) {
+        return true;
+    }
+    return false;
+};
+/** Check if a directory name is in the hardcoded ignore list */
+export const isHardcodedIgnoredDirectory = (name) => {
+    return DEFAULT_IGNORE_LIST.has(name);
+};
+/**
+ * Load .gitignore and .code-mapperignore rules from the repo root
+ * @param repoPath - Absolute path to the repository root
+ * @returns An `ignore` instance with all patterns, or null if no files found
+ */
+export const loadIgnoreRules = async (repoPath, options) => {
+    const ig = ignore();
+    let hasRules = false;
+    // Allow users to bypass .gitignore parsing (e.g. when .gitignore accidentally excludes source files)
+    const skipGitignore = options?.noGitignore ?? !!process.env.CODE_MAPPER_NO_GITIGNORE;
+    const filenames = skipGitignore
+        ? ['.code-mapperignore']
+        : ['.gitignore', '.code-mapperignore'];
+    for (const filename of filenames) {
+        try {
+            const content = await fs.readFile(nodePath.join(repoPath, filename), 'utf-8');
+            ig.add(content);
+            hasRules = true;
+        }
+        catch (err) {
+            const code = err.code;
+            if (code !== 'ENOENT') {
+                console.warn(`  Warning: could not read ${filename}: ${err.message}`);
+            }
+        }
+    }
+    return hasRules ? ig : null;
+};
+/**
+ * Create a glob-compatible ignore filter combining .gitignore/.code-mapperignore
+ * patterns with hardcoded ignore lists
+ * @param repoPath - Absolute path to the repository root
+ * @returns An IgnoreLike object for glob's `ignore` option with directory-level pruning
+ */
+export const createIgnoreFilter = async (repoPath, options) => {
+    const ig = await loadIgnoreRules(repoPath, options);
+    return {
+        ignored(p) {
+            // path-scurry returns POSIX paths — no normalization needed for `ignore` package
+            const rel = p.relative();
+            if (!rel)
+                return false;
+            // Check ignore file patterns
+            if (ig && ig.ignores(rel))
+                return true;
+            // Fall back to hardcoded rules
+            return shouldIgnorePath(rel);
+        },
+        childrenIgnored(p) {
+            // Fast path: check directory name against hardcoded list
+            // NOTE: dot-directories are primarily excluded by glob's `dot: false` in
+            // filesystem-walker.ts — this is defense-in-depth, do not remove `dot: false`
+            if (DEFAULT_IGNORE_LIST.has(p.name))
+                return true;
+            // Test both bare path and trailing-slash form for bare-name
+            // patterns (e.g. `local`) and dir-only patterns (e.g. `local/`)
+            if (ig) {
+                const rel = p.relative();
+                if (rel && (ig.ignores(rel) || ig.ignores(rel + '/')))
+                    return true;
+            }
+            return false;
+        },
+    };
+};

package/dist/config/supported-languages.d.ts

@@ -0,0 +1,23 @@
+/** @file supported-languages.ts @description Enum of programming languages supported by the tree-sitter parser */
+export declare enum SupportedLanguages {
+    JavaScript = "javascript",
+    TypeScript = "typescript",
+    Python = "python",
+    Java = "java",
+    C = "c",
+    CPlusPlus = "cpp",
+    CSharp = "csharp",
+    Go = "go",
+    Ruby = "ruby",
+    Rust = "rust",
+    PHP = "php",
+    Kotlin = "kotlin",
+    Swift = "swift"
+}
+/**
+ * All file extensions recognised by the code-mapper parser
+ *
+ * Derived from the extension checks in `getLanguageFromFilename`
+ * (core/ingestion/utils.ts) — keep in sync when adding languages
+ */
+export declare const SUPPORTED_EXTENSIONS: ReadonlySet<string>;

package/dist/config/supported-languages.js

@@ -0,0 +1,52 @@
+// code-mapper/src/config/supported-languages.ts
+/** @file supported-languages.ts @description Enum of programming languages supported by the tree-sitter parser */
+export var SupportedLanguages;
+(function (SupportedLanguages) {
+    SupportedLanguages["JavaScript"] = "javascript";
+    SupportedLanguages["TypeScript"] = "typescript";
+    SupportedLanguages["Python"] = "python";
+    SupportedLanguages["Java"] = "java";
+    SupportedLanguages["C"] = "c";
+    SupportedLanguages["CPlusPlus"] = "cpp";
+    SupportedLanguages["CSharp"] = "csharp";
+    SupportedLanguages["Go"] = "go";
+    SupportedLanguages["Ruby"] = "ruby";
+    SupportedLanguages["Rust"] = "rust";
+    SupportedLanguages["PHP"] = "php";
+    SupportedLanguages["Kotlin"] = "kotlin";
+    SupportedLanguages["Swift"] = "swift";
+})(SupportedLanguages || (SupportedLanguages = {}));
+/**
+ * All file extensions recognised by the code-mapper parser
+ *
+ * Derived from the extension checks in `getLanguageFromFilename`
+ * (core/ingestion/utils.ts) — keep in sync when adding languages
+ */
+export const SUPPORTED_EXTENSIONS = new Set([
+    // TypeScript
+    '.ts', '.tsx',
+    // JavaScript
+    '.js', '.jsx',
+    // Python
+    '.py',
+    // Java
+    '.java',
+    // C
+    '.c',
+    // C++ (including .h — parsed as C++ superset)
+    '.cpp', '.cc', '.cxx', '.h', '.hpp', '.hxx', '.hh',
+    // C#
+    '.cs',
+    // Go
+    '.go',
+    // Rust
+    '.rs',
+    // Kotlin
+    '.kt', '.kts',
+    // PHP
+    '.php', '.phtml', '.php3', '.php4', '.php5', '.php8',
+    // Ruby
+    '.rb', '.rake', '.gemspec',
+    // Swift
+    '.swift',
+]);

package/dist/core/augmentation/engine.d.ts

@@ -0,0 +1,22 @@
+/**
+ * @file engine.ts
+ * @description Lightweight enrichment of search patterns with knowledge graph context
+ *
+ * Called from platform hooks (Claude Code PreToolUse, Cursor beforeShellExecution)
+ * when an agent runs grep/glob/search
+ *
+ * Performance target: <500ms cold, <200ms warm
+ * Uses BM25 only (no embeddings) for speed; clusters rank internally but never surface
+ * Graceful failure: any error returns empty string
+ */
+/**
+ * Augment a search pattern with knowledge graph context
+ *
+ * 1) BM25 search for the pattern
+ * 2) Fetch callers/callees/processes for top matches
+ * 3) Rank by internal cluster cohesion (not exposed)
+ * 4) Format as structured text block
+ *
+ * Returns empty string on any error (graceful failure)
+ */
+export declare function augment(pattern: string, cwd?: string): Promise<string>;

package/dist/core/augmentation/engine.js

@@ -0,0 +1,232 @@
+// code-mapper/src/core/augmentation/engine.ts
+/**
+ * @file engine.ts
+ * @description Lightweight enrichment of search patterns with knowledge graph context
+ *
+ * Called from platform hooks (Claude Code PreToolUse, Cursor beforeShellExecution)
+ * when an agent runs grep/glob/search
+ *
+ * Performance target: <500ms cold, <200ms warm
+ * Uses BM25 only (no embeddings) for speed; clusters rank internally but never surface
+ * Graceful failure: any error returns empty string
+ */
+import path from 'path';
+import { listRegisteredRepos } from '../../storage/repo-manager.js';
+/** Find the best matching repo for a given working directory */
+async function findRepoForCwd(cwd) {
+    try {
+        const entries = await listRegisteredRepos({ validate: true });
+        const resolved = path.resolve(cwd);
+        // Normalize case on Windows (drive letters can differ: D: vs d:)
+        const isWindows = process.platform === 'win32';
+        const normalizedCwd = isWindows ? resolved.toLowerCase() : resolved;
+        const sep = path.sep;
+        // Longest matching repo path wins (most specific match)
+        let bestMatch = null;
+        let bestLen = 0;
+        for (const entry of entries) {
+            const repoResolved = path.resolve(entry.path);
+            const normalizedRepo = isWindows ? repoResolved.toLowerCase() : repoResolved;
+            // Match at path separator boundary to avoid false positives
+            // (e.g. /projects/code-mapperv2 should NOT match /projects/code-mapper)
+            let matched = false;
+            if (normalizedCwd === normalizedRepo) {
+                matched = true;
+            }
+            else if (normalizedCwd.startsWith(normalizedRepo + sep)) {
+                matched = true;
+            }
+            else if (normalizedRepo.startsWith(normalizedCwd + sep)) {
+                matched = true;
+            }
+            if (matched && normalizedRepo.length > bestLen) {
+                bestMatch = entry;
+                bestLen = normalizedRepo.length;
+            }
+        }
+        if (!bestMatch)
+            return null;
+        return {
+            name: bestMatch.name,
+            storagePath: bestMatch.storagePath,
+            lbugPath: path.join(bestMatch.storagePath, 'lbug'),
+        };
+    }
+    catch {
+        return null;
+    }
+}
+/**
+ * Augment a search pattern with knowledge graph context
+ *
+ * 1) BM25 search for the pattern
+ * 2) Fetch callers/callees/processes for top matches
+ * 3) Rank by internal cluster cohesion (not exposed)
+ * 4) Format as structured text block
+ *
+ * Returns empty string on any error (graceful failure)
+ */
+export async function augment(pattern, cwd) {
+    if (!pattern || pattern.length < 3)
+        return '';
+    const workDir = cwd || process.cwd();
+    try {
+        const repo = await findRepoForCwd(workDir);
+        if (!repo)
+            return '';
+        // Lazy-load lbug adapter
+        const { initLbug, executeQuery, isLbugReady } = await import('../../mcp/core/lbug-adapter.js');
+        const { searchFTSFromLbug } = await import('../search/bm25-index.js');
+        const repoId = repo.name.toLowerCase();
+        // Init LadybugDB if needed
+        if (!isLbugReady(repoId)) {
+            await initLbug(repoId, repo.lbugPath);
+        }
+        // Step 1: BM25 search (fast, no embeddings needed)
+        const bm25Results = await searchFTSFromLbug(pattern, 10, repoId);
+        if (bm25Results.length === 0)
+            return '';
+        // Step 2: Map BM25 file results to code symbols
+        const symbolMatches = [];
+        for (const result of bm25Results.slice(0, 5)) {
+            const escaped = result.filePath.replace(/'/g, "''");
+            try {
+                const symbols = await executeQuery(repoId, `
+          MATCH (n) WHERE n.filePath = '${escaped}'
+          AND n.name CONTAINS '${pattern.replace(/'/g, "''").split(/\s+/)[0]}'
+          RETURN n.id AS id, n.name AS name, labels(n) AS type, n.filePath AS filePath
+          LIMIT 3
+        `);
+                for (const sym of symbols) {
+                    symbolMatches.push({
+                        nodeId: sym.id || sym[0],
+                        name: sym.name || sym[1],
+                        type: sym.type || sym[2],
+                        filePath: sym.filePath || sym[3],
+                        score: result.score,
+                    });
+                }
+            }
+            catch { /* skip */ }
+        }
+        if (symbolMatches.length === 0)
+            return '';
+        // Step 3: Batch-fetch callers/callees/processes/cohesion (WHERE n.id IN [...])
+        const uniqueSymbols = symbolMatches.slice(0, 5).filter((sym, i, arr) => arr.findIndex(s => s.nodeId === sym.nodeId) === i);
+        if (uniqueSymbols.length === 0)
+            return '';
+        const idList = uniqueSymbols.map(s => `'${s.nodeId.replace(/'/g, "''")}'`).join(', ');
+        // Callers
+        const callersMap = new Map();
+        try {
+            const rows = await executeQuery(repoId, `
+        MATCH (caller)-[:CodeRelation {type: 'CALLS'}]->(n)
+        WHERE n.id IN [${idList}]
+        RETURN n.id AS targetId, caller.name AS name
+        LIMIT 15
+      `);
+            for (const r of rows) {
+                const tid = r.targetId || r[0];
+                const name = r.name || r[1];
+                if (tid && name) {
+                    if (!callersMap.has(tid))
+                        callersMap.set(tid, []);
+                    callersMap.get(tid).push(name);
+                }
+            }
+        }
+        catch { /* skip */ }
+        // Callees
+        const calleesMap = new Map();
+        try {
+            const rows = await executeQuery(repoId, `
+        MATCH (n)-[:CodeRelation {type: 'CALLS'}]->(callee)
+        WHERE n.id IN [${idList}]
+        RETURN n.id AS sourceId, callee.name AS name
+        LIMIT 15
+      `);
+            for (const r of rows) {
+                const sid = r.sourceId || r[0];
+                const name = r.name || r[1];
+                if (sid && name) {
+                    if (!calleesMap.has(sid))
+                        calleesMap.set(sid, []);
+                    calleesMap.get(sid).push(name);
+                }
+            }
+        }
+        catch { /* skip */ }
+        // Processes
+        const processesMap = new Map();
+        try {
+            const rows = await executeQuery(repoId, `
+        MATCH (n)-[r:CodeRelation {type: 'STEP_IN_PROCESS'}]->(p:Process)
+        WHERE n.id IN [${idList}]
+        RETURN n.id AS nodeId, p.heuristicLabel AS label, r.step AS step, p.stepCount AS stepCount
+      `);
+            for (const r of rows) {
+                const nid = r.nodeId || r[0];
+                const label = r.label || r[1];
+                const step = r.step || r[2];
+                const stepCount = r.stepCount || r[3];
+                if (nid && label) {
+                    if (!processesMap.has(nid))
+                        processesMap.set(nid, []);
+                    processesMap.get(nid).push(`${label} (step ${step}/${stepCount})`);
+                }
+            }
+        }
+        catch { /* skip */ }
+        // Cohesion (internal ranking signal)
+        const cohesionMap = new Map();
+        try {
+            const rows = await executeQuery(repoId, `
+        MATCH (n)-[:CodeRelation {type: 'MEMBER_OF'}]->(c:Community)
+        WHERE n.id IN [${idList}]
+        RETURN n.id AS nodeId, c.cohesion AS cohesion
+      `);
+            for (const r of rows) {
+                const nid = r.nodeId || r[0];
+                const coh = r.cohesion ?? r[1] ?? 0;
+                if (nid)
+                    cohesionMap.set(nid, coh);
+            }
+        }
+        catch { /* skip */ }
+        // Assemble enriched context
+        const enriched = [];
+        for (const sym of uniqueSymbols) {
+            enriched.push({
+                name: sym.name,
+                filePath: sym.filePath,
+                callers: (callersMap.get(sym.nodeId) || []).slice(0, 3),
+                callees: (calleesMap.get(sym.nodeId) || []).slice(0, 3),
+                processes: processesMap.get(sym.nodeId) || [],
+                cohesion: cohesionMap.get(sym.nodeId) || 0,
+            });
+        }
+        if (enriched.length === 0)
+            return '';
+        // Step 4: Rank by cohesion and format output
+        enriched.sort((a, b) => b.cohesion - a.cohesion);
+        const lines = [`[Code Mapper] ${enriched.length} related symbols found:`, ''];
+        for (const item of enriched) {
+            lines.push(`${item.name} (${item.filePath})`);
+            if (item.callers.length > 0) {
+                lines.push(`  Called by: ${item.callers.join(', ')}`);
+            }
+            if (item.callees.length > 0) {
+                lines.push(`  Calls: ${item.callees.join(', ')}`);
+            }
+            if (item.processes.length > 0) {
+                lines.push(`  Flows: ${item.processes.join(', ')}`);
+            }
+            lines.push('');
+        }
+        return lines.join('\n').trim();
+    }
+    catch {
+        // Graceful failure — never break the caller's tool
+        return '';
+    }
+}

package/dist/core/embeddings/embedder.d.ts

@@ -0,0 +1,35 @@
+/**
+ * @file embedder.ts
+ * @description MLX-accelerated code embedder via Python subprocess
+ *
+ * Replaces the previous ONNX/transformers.js embedder with Jina Code 1.5B
+ * running on Apple Silicon Metal via MLX. Fail-fast — no fallback.
+ *
+ * Model: jinaai/jina-code-embeddings-1.5b-mlx (1.54B params, 1536 dims, 32K context)
+ * Matryoshka truncation to 256 dims for optimal speed/quality tradeoff
+ */
+import { type EmbeddingConfig, type ModelProgress } from './types.js';
+/** Progress callback for model loading */
+export type ModelProgressCallback = (progress: ModelProgress) => void;
+/** Get the current inference device */
+export declare const getCurrentDevice: () => string | null;
+/**
+ * Initialize the MLX embedder (spawns Python subprocess, loads model)
+ */
+export declare const initEmbedder: (_onProgress?: ModelProgressCallback, _config?: Partial<EmbeddingConfig>) => Promise<any>;
+/** Check if the embedder is initialized and ready */
+export declare const isEmbedderReady: () => boolean;
+/** Get the embedder instance — not applicable for MLX, returns null */
+export declare const getEmbedder: () => any;
+/**
+ * Embed a single text string
+ */
+export declare const embedText: (text: string) => Promise<Float32Array>;
+/**
+ * Embed multiple texts in a single batch
+ */
+export declare const embedBatch: (texts: string[]) => Promise<Float32Array[]>;
+/** Convert Float32Array to number[] for LadybugDB storage */
+export declare const embeddingToArray: (embedding: Float32Array) => number[];
+/** Dispose the embedder subprocess */
+export declare const disposeEmbedder: () => Promise<void>;